Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7895
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
     itself
    -0.88
    6
    -0.87
    0
    -0.85
     TÉCNICA
    -0.85
    4
    -0.81
     compatri
    -0.81
    3
    -0.81
     oms
    -0.81
     Type
    -0.80
     gef
    -0.80
    POSITIVE LOGITS
    écri
    1.10
    arrivo
    1.01
    wuchs
    1.00
     spät
    0.99
     שלנו
    0.98
    焌
    0.96
    ingresso
    0.95
    achieve
    0.93
    artista
    0.93
    intéress
    0.93
    Activations Density 0.008%

    No Known Activations