© 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. 110511
    Prev
    Next
    INDEX
    Explanations

    Q: questions and architecture

    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
     FREQUENCY
    -0.82
     phổ
    -0.82
     Estructura
    -0.78
     relativement
    -0.77
     благода
    -0.77
    长度
    -0.76
     móc
    -0.74
     ILLUSTR
    -0.73
    inflammation
    -0.73
    iotensin
    -0.73
    POSITIVE LOGITS
     tect
    1.24
     form
    1.13
     functional
    1.11
     tectonic
    1.02
    tect
    1.01
     użytk
    0.99
     building
    0.96
     users
    0.96
    functional
    0.95
     kullanıcı
    0.94
    Activations Density 0.020%

    No Known Activations