© 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. 39564
    Prev
    Next
    INDEX
    Explanations

    split, base, noticed, enhance, APP, mercy, panel

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

    ongoing descriptions and strategies

    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
    0.45
     workbook
    0.44
     four
    0.43
     on
    0.43
    ắ
    0.41
     eight
    0.41
     Handbook
    0.38
     lt
    0.38
     six
    0.38
     probably
    0.38
    POSITIVE LOGITS
    Deposito
    0.42
    मार्
    0.41
     మరియు
    0.39
    וני
    0.39
    RELATIVA
    0.39
     आर्थिक
    0.38
     демокра
    0.38
    বাত
    0.38
    และความ
    0.38
    🏭
    0.38
    Activations Density 0.001%

    No Known Activations