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. 8211
    Prev
    Next
    INDEX
    Explanations

    HTML tags, URLs, code, metadata

    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
     and
    -1.57
     in
    -1.43
     Only
    -1.35
     with
    -1.35
     for
    -1.33
     revital
    -1.31
     Since
    -1.30
     by
    -1.28
     or
    -1.27
     only
    -1.26
    POSITIVE LOGITS
     !!!!
    1.50
     estándares
    1.38
     créer
    1.27
     trám
    1.25
    !!!!!!!
    1.21
     láp
    1.20
    !!!!!!
    1.17
     espectáculos
    1.16
     diseños
    1.16
    null
    1.14
    Activations Density 0.002%

    No Known Activations