© 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. 10088
    Prev
    Next
    INDEX
    Explanations

    creating new text rather than retrieving

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

    This neuron responds to tokens that serve as specific identifiers—proper nouns, variable names, or other domain-specific labels.

    oai_token-act-pair · o4-miniTriggered 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
    spark
    0.82
    控
    0.79
     días
    0.79
    ip
    0.78
     tyrannical
    0.76
    ียด
    0.75
    brechen
    0.75
    presumably
    0.75
    َس
    0.73
    epis
    0.73
    POSITIVE LOGITS
     aspire
    0.81
     สี
    0.80
     ณ
    0.75
     traverses
    0.74
     Dirt
    0.73
     x
    0.71
     at
    0.71
     เก็บ
    0.71
     defaults
    0.70
     sheds
    0.70
    Activations Density 0.000%

    No Known Activations