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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8180
    Prev
    Next
    INDEX
    Explanations

    Vibrio, carried, illon

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific notation in parentheses, particularly superscript numbers and negative exponents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    odin
    -0.82
    EDR
    -0.81
    tisgarh
    -0.80
    rikes
    -0.79
    vq
    -0.79
     Ecology
    -0.77
    餾
    -0.76
    orap
    -0.76
     acima
    -0.76
    sili
    -0.75
    POSITIVE LOGITS
     bencana
    0.77
     матч
    0.77
     масло
    0.73
    ARTICLE
    0.71
     Tel
    0.70
    บอก
    0.69
    playable
    0.68
     uniquely
    0.68
    ęs
    0.68
     Capit
    0.67
    Activations Density 0.028%

    No Known Activations