© 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. 34-GEMMASCOPE-RES-131K
    7. 110551
    Prev
    Next
    INDEX
    Explanations

    different kinds of

    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_34/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
    both
    -1.33
    actéristi
    -1.30
    𓍊
    -1.25
     diğer
    -1.23
    
    -1.22
    вгений
    -1.21
    ֶּ
    -1.20
     Москву
    -1.20
     Quando
    -1.19
    ྃ
    -1.19
    POSITIVE LOGITS
     kinds
    3.03
     types
    2.67
     kind
    2.28
     sized
    1.97
     from
    1.88
     but
    1.82
    種類の
    1.73
     than
    1.69
     type
    1.66
     parts
    1.64
    Activations Density 0.053%

    No Known Activations