© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 1942
    Prev
    Next
    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     :).
    0.52
     alleviating
    0.47
    :>
    0.46
    }\}$.
    0.46
     kurang
    0.45
     😄
    0.44
     ;-)
    0.44
     :-)
    0.42
    }\}$
    0.42
    .}}
    0.42
    POSITIVE LOGITS
    उनके
    0.45
    あなたの
    0.42
    あなたは
    0.42
    defendant
    0.41
    你會
    0.41
     Kecamatan
    0.41
    Bishop
    0.40
    政
    0.40
    惹
    0.39
    웰
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.