© 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. 11403
    Prev
    Next
    INDEX
    Explanations

    dialogue and questions

    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
     nutric
    -0.94
     instructor
    -0.93
     语
    -0.89
    それに
    -0.88
    집
    -0.86
     instructors
    -0.85
    見て
    -0.82
     umbro
    -0.82
    勸
    -0.82
     profesores
    -0.81
    POSITIVE LOGITS
     they
    1.28
     dialog
    1.02
     dialogue
    0.99
     mereka
    0.94
    dialogue
    0.94
    を果た
    0.94
     muerto
    0.93
    They
    0.91
    他们
    0.90
     Mereka
    0.90
    Activations Density 0.032%

    No Known Activations