© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73362
    Prev
    Next
    INDEX
    Explanations

    during a time period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    や
    -2.11
    と
    -2.11
    もあります
    -2.05
    休日
    -2.05
    そして
    -2.03
    右側
    -2.00
     has
    -1.99
     Tatsache
    -1.95
    などを
    -1.95
    時間を
    -1.95
    POSITIVE LOGITS
    providedIn
    2.86
    Según
    2.19
     the
    2.08
    為に
    2.06
    鄚
    2.03
    ものに
    2.02
     this
    2.00
    ၜ
    1.98
    垕
    1.96
    嘁
    1.95
    Activations Density 0.050%

    No Known Activations