© 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. 204126
    Prev
    Next
    INDEX
    Explanations

    AKC/FSS, contain, Audible, particularly

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

    version of

    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
     अनुशंसा
    0.47
    ホット
    0.47
    网红
    0.46
    唕
    0.46
     vuonna
    0.46
    热门
    0.46
    鉐
    0.45
     முடியும்
    0.45
    㑨
    0.44
     하늘
    0.43
    POSITIVE LOGITS
    4
    0.56
    2
    0.52
    6
    0.51
    يها
    0.48
    OW
    0.47
    7
    0.47
    erte
    0.47
    3
    0.46
    ERIC
    0.45
    '][
    0.44
    Activations Density 0.000%

    No Known Activations