Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7757
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     barely
    -0.89
     voulais
    -0.88
    飛機
    -0.84
     посту
    -0.79
     енер
    -0.77
    記錄
    -0.75
     connais
    -0.75
     honestly
    -0.74
     Keeping
    -0.74
     occasionally
    -0.73
    POSITIVE LOGITS
     commutation
    0.90
    dient
    0.88
    asp
    0.87
     FORT
    0.86
    刁
    0.86
    一愣
    0.85
     طريقة
    0.85
    finity
    0.83
    Ingrese
    0.82
     müh
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.