© 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. 112528
    Prev
    Next
    INDEX
    Explanations

    Strange words or foreign languages

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

    technology

    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
    所属
    0.45
     camaraderie
    0.43
     invigorating
    0.40
    询问
    0.40
    Positions
    0.39
     validType
    0.39
     所
    0.39
    传入
    0.39
     conveys
    0.38
    セックス
    0.38
    POSITIVE LOGITS
     साँप
    0.48
     გამოყენ
    0.47
     मैन
    0.46
     माइट
    0.46
     μην
    0.44
     जहर
    0.44
     ग्लूको
    0.44
     Medicines
    0.43
     medicina
    0.43
     Strange
    0.43
    Activations Density 0.001%

    No Known Activations