© 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. 10-GEMMASCOPE-RES-131K
    4. 654
    Prev
    Next
    INDEX
    Explanations

    case numbers and citations

    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
    ↵
    -2.19
     also
    -1.95
    Also
    -1.88
    Not
    -1.80
    Even
    -1.76
    ?
    -1.74
     Since
    -1.73
    It
    -1.71
     it
    -1.70
     began
    -1.70
    POSITIVE LOGITS
     trois
    1.81
    extremely
    1.77
    ༣
    1.72
    ඈ
    1.70
     plusieurs
    1.70
    beautiful
    1.68
    ωση
    1.68
     dát
    1.66
    —————
    1.66
    ukone
    1.66
    Activations Density 0.113%

    No Known Activations