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. 8678
    Prev
    Next
    INDEX
    Explanations

    Disjunctive cognition

    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
     XIV
    -0.94
    XIV
    -0.90
     Teen
    -0.86
     Instruments
    -0.82
    んび
    -0.79
     fourteenth
    -0.79
     Tudor
    -0.77
    ‶
    -0.76
     fifteenth
    -0.76
     volleyball
    -0.75
    POSITIVE LOGITS
     twelfth
    1.05
     Norman
    0.97
     norman
    0.91
     XII
    0.88
    Norman
    0.78
     Béla
    0.73
     Peterborough
    0.73
     Tô
    0.73
     Norma
    0.71
    Norma
    0.71
    Activations Density 0.041%

    No Known Activations