© 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. 120263
    Prev
    Next
    INDEX
    Explanations

    words like free and brand

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

    concise or brief responses

    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
    ж
    0.43
    稿
    0.42
     belladone
    0.41
    補充
    0.40
    જર
    0.40
     バイ
    0.40
    plasia
    0.40
    NCc
    0.39
    bai
    0.39
    漆
    0.39
    POSITIVE LOGITS
     indemn
    0.49
     साझेदारी
    0.47
    lük
    0.46
     Pius
    0.44
     indigestion
    0.44
     хотя
    0.43
     فع
    0.43
     efectivo
    0.43
     pid
    0.42
     Tasty
    0.42
    Activations Density 0.000%

    No Known Activations