© 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. 22-GEMMASCOPE-RES-131K
    7. 11475
    Prev
    Next
    INDEX
    Explanations

    configuration blocks and code

    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_22/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
     If
    -1.00
    ickness
    -0.96
    南部
    -0.91
     amelior
    -0.86
     Since
    -0.86
    For
    -0.86
     ścian
    -0.85
     did
    -0.85
     diesen
    -0.84
    映射
    -0.83
    POSITIVE LOGITS
    饜
    1.33
     westfalen
    1.31
    傒
    1.19
    鲼
    1.17
     diseños
    1.16
    Ꮂ
    1.16
     niedersachsen
    1.13
     ایالات
    1.13
    摀
    1.13
     geni
    1.10
    Activations Density 0.025%

    No Known Activations