© 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. 224212
    Prev
    Next
    INDEX
    Explanations

    reporting, found, failure, vulnerabilities, happens, lines

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

    extra spatial dimensions

    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
    _
    0.61
    CC
    0.53
     quantile
    0.50
    zel
    0.48
    ever
    0.48
    +
    0.47
    ader
    0.47
    CN
    0.46
    जित
    0.46
    aper
    0.46
    POSITIVE LOGITS
     მდ
    0.54
    نیا
    0.54
    媧
    0.54
    秾
    0.53
    期间
    0.49
     бри
    0.49
     preceded
    0.48
    鹂
    0.47
    மில்லை
    0.47
    软件包
    0.47
    Activations Density 0.002%

    No Known Activations