© 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. 185920
    Prev
    Next
    INDEX
    Explanations

    Brentwood Eng farmland

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

    pointers and array indexing

    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
    م
    0.54
    ه
    0.54
    造
    0.48
    a
    0.47
    諦
    0.46
    制造
    0.46
    м
    0.45
    로
    0.45
    வின்
    0.44
    商标
    0.44
    POSITIVE LOGITS
     ভারতীয়রা
    0.49
    FBSDKApp
    0.48
     keluarga
    0.48
     ラン
    0.47
    ุ่น
    0.46
    waitSeconds
    0.46
     tierras
    0.46
     Nigerians
    0.45
     terjadinya
    0.45
     slidesToShow
    0.45
    Activations Density 0.001%

    No Known Activations