© 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. 10-GEMMASCOPE-RES-131K
    7. 752
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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_10/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
     cinquième
    -1.58
    が無い
    -1.57
    が少ない
    -1.49
     listes
    -1.49
    Uso
    -1.47
    arrive
    -1.45
     BENE
    -1.45
    がなく
    -1.44
    Dentro
    -1.44
    ING
    -1.44
    POSITIVE LOGITS
     one
    1.92
     for
    1.88
     and
    1.84
     three
    1.70
    ="
    1.67
     should
    1.65
     two
    1.63
    frac
    1.58
     five
    1.56
     section
    1.56
    Activations Density 0.001%

    No Known Activations