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. 34
    Prev
    Next
    INDEX
    Explanations

    audio hardware and software

    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
     step
    -0.88
    anko
    -0.76
    邇
    -0.75
     Genome
    -0.74
    örd
    -0.72
     FSA
    -0.71
    เล่น
    -0.71
     mémor
    -0.68
     hostess
    -0.67
    atsch
    -0.67
    POSITIVE LOGITS
     Neve
    1.23
     outboard
    1.09
    vintage
    1.02
    ンテージ
    1.02
    Passive
    1.02
     SSL
    0.99
    Vintage
    0.98
     passive
    0.96
    passive
    0.96
     tube
    0.94
    Activations Density 0.013%

    No Known Activations