© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112651
    Prev
    Next
    INDEX
    Explanations

    educational achievement

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

    advice & explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    n
    0.53
    div
    0.51
    frac
    0.48
     proponent
    0.47
     heer
    0.46
    Socket
    0.46
     div
    0.45
     medium
    0.44
     "\
    0.44
     carbur
    0.43
    POSITIVE LOGITS
    ება
    0.50
    兒子
    0.50
    ammed
    0.48
    ే
    0.48
    េះ
    0.45
     Associations
    0.44
     शुर
    0.44
    經過
    0.44
    ajno
    0.44
    銠
    0.44
    Activations Density 0.001%

    No Known Activations