© 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. 137946
    Prev
    Next
    INDEX
    Explanations

    classified descriptions

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

    HP and Webpack

    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
    directories
    0.57
     शिफ्ट
    0.52
    ikal
    0.52
    ŏ
    0.52
    력을
    0.51
    uld
    0.50
    ulen
    0.50
    톨
    0.50
    𝚞
    0.50
     multitudes
    0.49
    POSITIVE LOGITS
     indifferent
    0.46
     Saying
    0.45
     (
    0.44
     simulates
    0.43
    แต่
    0.42
     outcast
    0.42
     Invest
    0.42
     vilken
    0.42
     setUp
    0.41
     Valuation
    0.41
    Activations Density 0.000%

    No Known Activations