© 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. 208797
    Prev
    Next
    INDEX
    Explanations

    Registration Portal

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

    friend smile pigeons

    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
     ايضا
    0.45
    也很
    0.45
     ook
    0.42
     ဆ
    0.42
    TERS
    0.41
    粉丝
    0.41
     noemen
    0.41
     也
    0.41
    蓝牙
    0.40
     nejs
    0.40
    POSITIVE LOGITS
    democracy
    0.44
     मतदान
    0.44
     homomorphism
    0.43
     artikel
    0.42
     எடுத்துக்கா
    0.42
    urah
    0.42
     مقاله
    0.41
    righteous
    0.41
     पत्नी
    0.41
    ಫ
    0.41
    Activations Density 0.000%

    No Known Activations