© 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. 152733
    Prev
    Next
    INDEX
    Explanations

    confidence intervals, collection of

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

    describing something specific

    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
     untuk
    0.47
     வெளியில்
    0.44
     சாப்பிட
    0.43
    刊
    0.43
     cena
    0.43
     für
    0.43
     نوم
    0.43
     Kant
    0.42
    ERNAL
    0.42
    $),
    0.42
    POSITIVE LOGITS
     equaling
    0.48
     sightings
    0.47
     alapján
    0.47
    Deze
    0.47
    ँव
    0.46
    ू
    0.46
    ूक
    0.45
     breakdowns
    0.44
    abulary
    0.44
    ूण
    0.44
    Activations Density 0.000%

    No Known Activations