© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 239190
    Prev
    Next
    INDEX
    Explanations

    individual basis or risk profile

    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
    ي
    0.53
    ل
    0.53
    л
    0.51
    c
    0.49
    Spare
    0.48
     Spare
    0.47
    Ding
    0.46
    Room
    0.46
    ط
    0.46
    ذ
    0.46
    POSITIVE LOGITS
     champion
    0.54
     चैंपियन
    0.54
     poignant
    0.49
     championed
    0.49
     creatively
    0.47
     culturali
    0.46
     เจ้า
    0.45
     文化
    0.45
    isière
    0.44
    arci
    0.43
    Activations Density 0.000%

    No Known Activations