© 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. 194564
    Prev
    Next
    INDEX
    Explanations

    written by

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

    indistinguishable, admittedly, yet, predictably

    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
    ટ્સ
    0.55
    কো
    0.52
    كا
    0.50
    カー
    0.49
    ロ
    0.47
    क
    0.47
    MAS
    0.46
    കോ
    0.46
    γκε
    0.46
     Rotterdam
    0.45
    POSITIVE LOGITS
    umet
    0.43
    “(
    0.43
    “[
    0.42
    ^*(
    0.42
     builtin
    0.42
     bosonic
    0.42
     wheeled
    0.41
     temperature
    0.41
     temperatur
    0.41
     bison
    0.41
    Activations Density 0.000%

    No Known Activations