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. 22-GEMMASCOPE-RES-131K
    4. 11753
    Prev
    Next
    INDEX
    Explanations

    directory names and aliases

    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_22/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
    の方も
    -1.02
     wilden
    -0.99
     loud
    -0.98
    gigabyte
    -0.95
    ubakar
    -0.95
    levis
    -0.94
    smoked
    -0.94
    nordic
    -0.93
    california
    -0.93
    berserk
    -0.92
    POSITIVE LOGITS
    Détails
    1.08
    Mostrar
    1.00
    ϳ
    0.98
    details
    0.97
     nunc
    0.96
    片刻
    0.96
     luminos
    0.96
    ப்
    0.96
    Listar
    0.95
     groupBox
    0.94
    Activations Density 0.013%

    No Known Activations