© 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. 2413
    Prev
    Next
    INDEX
    Explanations

    `+ *` or `+/*`

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

    code diffs and additions

    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
     animaux
    0.53
    UILLER
    0.53
     ビタミン
    0.53
     細胞
    0.52
    ORDAN
    0.52
     proteínas
    0.52
     酸
    0.52
     artères
    0.51
     protéines
    0.50
     amyloid
    0.50
    POSITIVE LOGITS
    ↵
    0.64
    import
    0.54
    function
    0.49
    <code>
    0.49
    /**
    0.48
    using
    0.47
     moderate
    0.47
     added
    0.47
    i
    0.47
     que
    0.46
    Activations Density 0.000%

    No Known Activations