© 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. 118839
    Prev
    Next
    INDEX
    Explanations

    Global war disclaimer

    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
    抉
    -0.98
    чя
    -0.91
     aérea
    -0.82
     coincides
    -0.79
     temática
    -0.78
    Koordinaten
    -0.76
    akujem
    -0.76
     how
    -0.73
    таки
    -0.73
     sutil
    -0.73
    POSITIVE LOGITS
    鶩
    0.88
    繼續
    0.83
    為什麼
    0.82
     Nagasaki
    0.81
    这两
    0.81
     Kenyatta
    0.80
     regering
    0.79
     Robbery
    0.79
    久しぶり
    0.78
     derselbe
    0.78
    Activations Density 0.000%

    No Known Activations