© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211674
    Prev
    Next
    INDEX
    Explanations

    airline, database, collectors, repeated doses, swimming

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

    chief complaint, cost, scale, intermittent

    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
    Negative Logits
     Λ
    0.55
    lek
    0.49
     BMW
    0.47
     Θ
    0.46
     Там
    0.46
     ε
    0.46
     Αγ
    0.45
     Έ
    0.45
     Imagination
    0.44
     കൂ
    0.44
    POSITIVE LOGITS
    WART
    0.57
    ilium
    0.53
    s
    0.48
    il
    0.47
    wg
    0.47
    ilization
    0.47
    subtype
    0.46
    serious
    0.46
    ้อง
    0.45
    followlike
    0.45
    Activations Density 0.000%

    No Known Activations