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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11580
    Prev
    Next
    INDEX
    Explanations

    put the

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

    The neuron fires strongly on relatively rare, content-bearing words (longer or less common terms) regardless of part of speech.

    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
     avuto
    0.92
     имели
    0.85
     ribu
    0.84
     avevano
    0.84
    했습니다
    0.82
    
    0.82
     акча
    0.80
     hanno
    0.78
     мають
    0.75
    贼
    0.75
    POSITIVE LOGITS
     Últ
    0.79
    istics
    0.77
     Já
    0.77
    鯵
    0.77
     Expertise
    0.76
    expertise
    0.75
     Encoding
    0.75
     JPanel
    0.74
    Psych
    0.73
     Usuario
    0.73
    Activations Density 0.000%

    No Known Activations