© 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. 154674
    Prev
    Next
    INDEX
    Explanations

    distress, hammer, system, Texas

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

    internal code and infrastructure

    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
    ESIS
    0.54
    Td
    0.46
     cosmetic
    0.45
    SD
    0.45
    CV
    0.45
    ﱢ
    0.45
     camera
    0.44
    TV
    0.44
    Color
    0.44
     ልጅ
    0.43
    POSITIVE LOGITS
    zend
    0.45
     وار
    0.44
    였
    0.44
    gitignore
    0.42
    ార్
    0.41
    biz
    0.41
    吨
    0.41
     Józ
    0.41
    هار
    0.40
     trakt
    0.40
    Activations Density 0.000%

    No Known Activations