© 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. 163697
    Prev
    Next
    INDEX
    Explanations

    Analysts Saying, system status

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

    novel method or description

    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
     promulgating
    0.48
     heer
    0.43
    湿度
    0.43
    沇
    0.42
    啝
    0.42
    ћин
    0.42
    ដល់
    0.42
     кожен
    0.41
    zetten
    0.41
     સરકાર
    0.41
    POSITIVE LOGITS
    ;
    0.53
    نگی
    0.51
    ,'
    0.46
     '
    0.44
    ।
    0.43
     Split
    0.43
    ะ
    0.43
    ashire
    0.42
     Facilities
    0.42
    genome
    0.42
    Activations Density 0.000%

    No Known Activations