© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 6919
    Prev
    Next
    INDEX
    Explanations

    social media links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    in
    1.02
     in
    0.89
     to
    0.86
    on
    0.82
     for
    0.82
    ী
    0.77
    or
    0.76
     by
    0.75
     with
    0.75
    ,
    0.73
    POSITIVE LOGITS
     maíz
    0.82
     możli
    0.80
     maje
    0.79
     inglesa
    0.79
     glioma
    0.77
     demuestra
    0.75
     pedir
    0.75
    ない
    0.74
     placées
    0.74
    分之一
    0.73
    Activations Density 0.666%

    No Known Activations