© 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. 192507
    Prev
    Next
    INDEX
    Explanations

    stimulating serotonin, rocker switch, facility providers

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

    contains other items

    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
    The
    0.43
     The
    0.42
     fuerza
    0.42
    િક
    0.42
     dati
    0.41
     Equations
    0.41
     produziert
    0.41
     {\
    0.40
    َن
    0.40
     Combining
    0.40
    POSITIVE LOGITS
    netlify
    0.52
    isAuthenticated
    0.49
    RelativeTo
    0.48
    intos
    0.48
    爛
    0.47
    φάλ
    0.47
    ዞ
    0.47
    clad
    0.47
     लय
    0.46
    Lod
    0.46
    Activations Density 0.000%

    No Known Activations