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. 11932
    Prev
    Next
    INDEX
    Explanations

    dialogue and reporting speech

    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
     番目
    -1.03
    see
    -1.00
    inosa
    -0.94
    itaji
    -0.91
     zostanie
    -0.89
     zastos
    -0.89
     parametri
    -0.88
    vidla
    -0.88
    さあ
    -0.88
    ագ
    -0.87
    POSITIVE LOGITS
     lámpara
    1.07
     Aufwand
    1.05
     čás
    1.00
    direkt
    1.00
     said
    0.99
     włosów
    0.96
    rektor
    0.96
    gül
    0.96
     interview
    0.95
     pprint
    0.95
    Activations Density 0.019%

    No Known Activations