© 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. 98856
    Prev
    Next
    INDEX
    Explanations

    average height of geographic divisions

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

    Genshin Impact, Elden Ring

    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
    lift
    0.45
    0
    0.44
    laces
    0.44
    api
    0.43
    ourt
    0.41
    accompagn
    0.40
    habilitation
    0.39
    otom
    0.39
    add
    0.39
    urther
    0.39
    POSITIVE LOGITS
    ジュン
    0.50
     HEIGHT
    0.49
     ダーク
    0.48
     laver
    0.47
     STRING
    0.46
     bilhões
    0.46
    -/
    0.45
     jū
    0.45
     calculado
    0.45
     trouva
    0.45
    Activations Density 0.002%

    No Known Activations