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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12172
    Prev
    Next
    INDEX
    Explanations

    its Supporting Information files

    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
     یا
    -1.30
     kategor
    -1.28
    หรือ
    -1.23
     katalog
    -1.23
     faktor
    -1.17
     kompati
    -1.16
     reflek
    -1.10
     kré
    -1.09
     deklar
    -1.09
     livres
    -1.06
    POSITIVE LOGITS
    öbb
    0.94
    k
    0.94
    Three
    0.94
     k
    0.93
     included
    0.92
    SVN
    0.92
     incluyendo
    0.91
     has
    0.91
    dialement
    0.91
    K
    0.89
    Activations Density 0.004%

    No Known Activations