© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4896
    Prev
    Next
    INDEX
    Explanations

    programming keywords define set def

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is activated by numeric tokens representing decimal numbers (i.e., floating-point values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "redefine" or its variants (like "redefined", "redefining").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language that signals defining or redefining concepts, especially verbs indicating redefinition or clarification.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Мар
    0.94
    高兴
    0.92
    Mits
    0.86
    ">${
    0.85
    Five
    0.84
    Nich
    0.84
    璎
    0.82
    MAGIC
    0.79
    맣
    0.78
    
    0.78
    POSITIVE LOGITS
     the
    0.98
     Sana
    0.92
     Persona
    0.86
    the
    0.84
     Selena
    0.82
    യും
    0.80
    0.80
     Google
    0.78
     Sólo
    0.77
     uniquely
    0.76
    Activations Density 0.000%

    No Known Activations