© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11401
    Prev
    Next
    INDEX
    Explanations

    version specifiers

    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
    发动
    -0.94
     Antilles
    -0.93
    くちゃ
    -0.92
     ross
    -0.90
    たまた
    -0.89
    ḏ
    -0.89
     some
    -0.88
     seid
    -0.88
    CUSS
    -0.88
     there
    -0.88
    POSITIVE LOGITS
     essenziale
    1.10
     ilyen
    1.09
     olika
    1.06
     fühlte
    1.05
     suchte
    1.02
     reager
    0.98
     viktigt
    0.97
    From
    0.97
    Angebot
    0.95
    سا
    0.93
    Activations Density 0.003%

    No Known Activations