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. 8655
    Prev
    Next
    INDEX
    Explanations

    exception and runtime errors

    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
    ąż
    -0.90
     CORRE
    -0.82
    而后
    -0.82
     stammt
    -0.81
    hlander
    -0.80
     agreeable
    -0.77
    atcher
    -0.77
    の関係
    -0.77
    Asian
    -0.76
     решил
    -0.76
    POSITIVE LOGITS
    lardan
    0.90
    ParseException
    0.85
    Cevap
    0.81
    Flesh
    0.79
    niku
    0.79
     wyst
    0.78
     surfers
    0.78
     klass
    0.78
    ֶר
    0.78
    ameran
    0.77
    Activations Density 0.003%

    No Known Activations