© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109760
    Prev
    Next
    INDEX
    Explanations

    league names and categories

    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
     Educación
    -1.00
     Construcción
    -0.96
     Calidad
    -0.96
     Educação
    -0.93
     Trabalho
    -0.91
     TRABAJO
    -0.89
    ffective
    -0.88
     franqu
    -0.88
     sinyal
    -0.87
     Producción
    -0.86
    POSITIVE LOGITS
     Observ
    1.07
    يال
    1.02
     blatantly
    0.95
     even
    0.90
     universally
    0.90
     noticeably
    0.89
     reasonably
    0.86
     americana
    0.85
     occasionally
    0.83
    todo
    0.82
    Activations Density 0.178%

    No Known Activations