© 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. 110585
    Prev
    Next
    INDEX
    Explanations

    there is/are/have

    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
     other
    -1.23
     some
    -1.11
    .‏
    -0.96
     also
    -0.94
     другие
    -0.91
     otras
    -0.89
     пыта
    -0.87
     another
    -0.87
     بعض
    -0.87
     lại
    -0.83
    POSITIVE LOGITS
     couldn
    1.17
     verhe
    1.03
     scarcely
    1.02
     few
    1.02
     règles
    0.99
    Couldn
    0.98
     hardly
    0.94
    perhaps
    0.93
    couldn
    0.91
    诧
    0.90
    Activations Density 0.042%

    No Known Activations