© 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. 151
    Prev
    Next
    INDEX
    Explanations

    comparison of timeframes

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

    guidance for calculations and estimates

    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
     perfeito
    0.41
     المطلوب
    0.38
    这一切
    0.38
    <unused76>
    0.37
    阿拉伯
    0.37
    <unused81>
    0.37
     সবই
    0.37
    মর
    0.36
    ถูกต้อง
    0.36
     encomendas
    0.36
    POSITIVE LOGITS
     S
    0.47
     simpler
    0.46
     more
    0.44
     less
    0.43
     D
    0.43
     slower
    0.43
     longer
    0.42
     tend
    0.42
     broader
    0.42
     consider
    0.42
    Activations Density 0.000%

    No Known Activations