© 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. 112699
    Prev
    Next
    INDEX
    Explanations

    political affiliation or affiliation

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

    modelversions of models and sizes

    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
     మీకు
    0.52
     ello
    0.50
    的其他
    0.49
     '.</
    0.49
    rando
    0.48
     ı
    0.45
     mediterr
    0.45
    🧿
    0.44
     ఆడ
    0.43
     lore
    0.43
    POSITIVE LOGITS
    鏑
    0.52
     Twain
    0.44
    ﾋ
    0.44
    projectile
    0.44
    教師
    0.44
     electoral
    0.43
     Pr
    0.43
     Political
    0.42
     Einzel
    0.42
    未満
    0.42
    Activations Density 0.000%

    No Known Activations