© 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. 24469
    Prev
    Next
    INDEX
    Explanations

    Green Jersey

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

    strategic depth and voting

    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
     avrebbe
    0.47
     ս
    0.46
     собственные
    0.46
     ն
    0.45
     상당
    0.44
     سامنے
    0.43
    cier
    0.43
    媾
    0.43
     عن
    0.42
     परिचय
    0.41
    POSITIVE LOGITS
     divisions
    0.45
    io
    0.44
    lions
    0.44
     Divisions
    0.44
     consumable
    0.43
    يق
    0.43
     Plex
    0.42
    guru
    0.42
     VFX
    0.42
     skateboarding
    0.42
    Activations Density 0.000%

    No Known Activations