© 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. 63499
    Prev
    Next
    INDEX
    Explanations

    items and instructions

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

    time duration

    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
    '/>
    0.46
    امر
    0.42
     platinum
    0.41
     hapless
    0.41
     mittels
    0.41
     gemüt
    0.41
     amiable
    0.41
     آن
    0.40
    ünstler
    0.40
    </h3>
    0.40
    POSITIVE LOGITS
    Typically
    0.52
    केल
    0.50
    すごく
    0.50
    Hãy
    0.48
     typically
    0.48
    typically
    0.47
     Typically
    0.47
    ড়ে
    0.45
    ማ
    0.44
    อย
    0.43
    Activations Density 0.000%

    No Known Activations