© 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. 145364
    Prev
    Next
    INDEX
    Explanations

    positive language keywords

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

    computer science and hardware

    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
    ΡΑ
    0.41
    و
    0.41
    amme
    0.40
    炘
    0.40
     anden
    0.39
    <sup>
    0.39
    ק
    0.39
    Gast
    0.38
    ו
    0.38
     IP
    0.38
    POSITIVE LOGITS
    avasena
    0.55
    atthena
    0.54
     chuột
    0.53
    édon
    0.51
     ಒಳ್ಳೆಯ
    0.50
    esség
    0.49
     positivas
    0.49
     venge
    0.49
     pozitiv
    0.49
     Orta
    0.47
    Activations Density 0.000%

    No Known Activations