© 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. 133687
    Prev
    Next
    INDEX
    Explanations

    question and swimming

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

    Url :

    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
    افظ
    0.51
    压力
    0.48
    华
    0.45
    扯
    0.45
    相关
    0.44
    ్యూ
    0.44
    保存
    0.43
    的工作
    0.43
    后面的
    0.43
     Statement
    0.43
    POSITIVE LOGITS
    al
    0.46
    m
    0.46
    c
    0.45
     NFS
    0.45
    ფილი
    0.44
    p
    0.43
    Instagram
    0.43
    stainless
    0.43
    inherited
    0.43
    twenty
    0.43
    Activations Density 0.000%

    No Known Activations