© 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. 202071
    Prev
    Next
    INDEX
    Explanations

    exciting light source

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

    requirements 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
    fand
    0.44
     tract
    0.43
    $
    0.43
     curly
    0.42
     helfen
    0.42
    駆動
    0.42
    ೮
    0.42
    𝐛
    0.41
     the
    0.41
     cyber
    0.40
    POSITIVE LOGITS
     MERCHANT
    0.45
    পার
    0.43
    లు
    0.43
    Articulation
    0.43
     Raquel
    0.42
    ruari
    0.42
     শ্রীমতি
    0.42
    啞
    0.42
    ровать
    0.42
    шот
    0.42
    Activations Density 0.000%

    No Known Activations