© 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. 86701
    Prev
    Next
    INDEX
    Explanations

    when followed by seasons

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

    accept, setups, depending, search, pizza

    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
    客服
    0.58
     الثانية
    0.57
    ルール
    0.56
    逺
    0.55
     potř
    0.52
    撲
    0.52
    运维
    0.50
     čovjek
    0.49
    貳
    0.49
    雒
    0.49
    POSITIVE LOGITS
    a
    0.65
    t
    0.53
     as
    0.52
     fring
    0.50
    teg
    0.50
    I
    0.50
    tag
    0.50
    her
    0.49
    leg
    0.48
    theta
    0.48
    Activations Density 0.000%

    No Known Activations