© 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. 147775
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

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

    combining values or results, often financial or quantitative

    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
     Sebelum
    0.42
     observación
    0.41
    Después
    0.40
     warmest
    0.40
    <h2>
    0.39
     Như
    0.39
     இஸ்
    0.39
     Rússia
    0.38
     அவ்
    0.38
     postérieurs
    0.38
    POSITIVE LOGITS
    in
    0.52
    elig
    0.48
     bohat
    0.47
     äh
    0.47
    ero
    0.45
    achar
    0.45
    formerly
    0.45
    of
    0.44
    اً
    0.44
     finanzi
    0.43
    Activations Density 0.000%

    No Known Activations