© 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. 110615
    Prev
    Next
    INDEX
    Explanations

    date stamped or shelf life

    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
     accessToken
    -0.84
    ūs
    -0.77
     tobacco
    -0.73
     wool
    -0.72
    Frequency
    -0.72
     fuerte
    -0.71
     tourism
    -0.71
     timber
    -0.71
    buildings
    -0.71
     naturel
    -0.70
    POSITIVE LOGITS
     date
    1.80
     expiration
    1.76
     expiry
    1.64
     shelf
    1.45
     Date
    1.35
     expiring
    1.34
     dates
    1.34
     expired
    1.30
    date
    1.28
    Expiration
    1.27
    Activations Density 0.016%

    No Known Activations