© 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. 118706
    Prev
    Next
    INDEX
    Explanations

    probability and observation

    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
    setTime
    -0.79
     defin
    -0.77
    ».
    -0.75
     protagon
    -0.74
     necess
    -0.74
     Bru
    -0.73
    ABASES
    -0.73
     giai
    -0.73
     Kron
    -0.73
    ')[
    -0.73
    POSITIVE LOGITS
     sample
    1.29
     observed
    1.20
     samples
    1.08
     sampling
    1.00
    sample
    1.00
     resourceCulture
    0.97
     outcomes
    0.96
     observations
    0.95
     this
    0.92
    ariate
    0.92
    Activations Density 0.037%

    No Known Activations