© 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. 131364
    Prev
    Next
    INDEX
    Explanations

    material away, range box, Log ically

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

    oil spreads disruptions

    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
     防止
    0.50
     adoptar
    0.47
     будем
    0.46
     ρ
    0.46
    采用
    0.46
     ход
    0.45
     كيلو
    0.45
     জীব
    0.45
    一時
    0.45
     开始
    0.44
    POSITIVE LOGITS
     gameplay
    0.47
    Gameplay
    0.47
     Upstairs
    0.46
     Gunners
    0.46
    뀌
    0.45
    âtre
    0.44
     smell
    0.44
     PlayStation
    0.44
     Creature
    0.43
     overly
    0.43
    Activations Density 0.000%

    No Known Activations