© 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. 125230
    Prev
    Next
    INDEX
    Explanations

    unveil his, pay the, books on, flavors of

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

    spilled across, fills, country, capacitor, permissions, shatter

    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
     universidad
    0.58
     Universidad
    0.51
     UNIV
    0.48
     erythro
    0.48
     Undergraduate
    0.46
    需
    0.45
     Basement
    0.45
    Universidad
    0.45
     Villanova
    0.45
     Universität
    0.45
    POSITIVE LOGITS
    enzel
    0.47
     çöze
    0.43
     daje
    0.42
     المعادله
    0.42
     رئيس
    0.41
    <div>
    0.41
     convexe
    0.41
     hepinize
    0.41
    ę
    0.40
     venu
    0.40
    Activations Density 0.000%

    No Known Activations