© 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. 1389
    Prev
    Next
    INDEX
    Explanations

    character substitution

    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
     richiest
    0.48
     operands
    0.48
    患者
    0.46
    㑔
    0.46
     enanti
    0.45
    ूरती
    0.44
    素敵
    0.44
    对称
    0.43
    取决于
    0.43
    রি
    0.42
    POSITIVE LOGITS
     جيم
    0.46
     ב
    0.45
     מש
    0.45
     โ
    0.44
     वन
    0.43
     ט
    0.43
     мате
    0.42
     ג
    0.42
     يستخدم
    0.42
     בה
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.