© 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. 186010
    Prev
    Next
    INDEX
    Explanations

    World potential

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

    readonly array conditional

    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
    醿
    0.54
    <unused53>
    0.53
     قاسمی
    0.53
    埥
    0.52
    кової
    0.51
     ক্লাশ
    0.51
    鉋
    0.50
    وتی
    0.49
    ے۔
    0.49
    یتے
    0.49
    POSITIVE LOGITS
     potenc
    0.52
     Philadelphia
    0.52
     potencial
    0.52
     hry
    0.52
     pre
    0.50
     potential
    0.50
     stanje
    0.50
     homepage
    0.49
     subst
    0.49
    0.49
    Activations Density 0.000%

    No Known Activations