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. 7699
    Prev
    Next
    INDEX
    Explanations

    interpretation

    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
    cress
    -0.77
     Yunus
    -0.76
    inate
    -0.74
    distan
    -0.71
     PLO
    -0.70
    adam
    -0.70
     Nana
    -0.69
    serialize
    -0.69
    wirkungen
    -0.69
     voran
    -0.68
    POSITIVE LOGITS
     interpretation
    5.78
    interpretation
    4.69
     interpretations
    4.69
     Interpretation
    4.56
    Interpretation
    4.31
     interpretación
    4.19
     interpret
    4.16
     interpreted
    4.13
     interpreting
    3.98
     interprets
    3.98
    Activations Density 0.064%

    No Known Activations