© 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. 161278
    Prev
    Next
    INDEX
    Explanations

    carving or replica

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

    fabricating information

    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
    摹
    0.52
    ూరు
    0.51
    用户信息
    0.50
    torio
    0.50
    牍
    0.48
    diendo
    0.47
    μένη
    0.46
    ウト
    0.46
    孱
    0.46
    curso
    0.45
    POSITIVE LOGITS
    Eye
    0.45
    LEN
    0.43
     Grafik
    0.43
     counteract
    0.43
    RF
    0.43
    RANGE
    0.43
     CREAM
    0.43
    Ya
    0.42
     are
    0.41
     INSERT
    0.41
    Activations Density 0.001%

    No Known Activations