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. 8579
    Prev
    Next
    INDEX
    Explanations

    routines called, filters, duplicate, incomplete, all identifiers

    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
    めちゃくちゃ
    -1.29
     your
    -1.21
    <code>
    -1.13
    Idk
    -1.09
     idk
    -1.07
     Idk
    -1.07
    <em>
    -1.04
    hline
    -1.03
    rás
    -1.02
     technisch
    -1.02
    POSITIVE LOGITS
     we
    1.52
     now
    1.20
     occafion
    1.12
     ourselves
    1.02
     semuanya
    0.98
    ='".$
    0.98
    takings
    0.96
     mung
    0.94
     sez
    0.94
     routines
    0.92
    Activations Density 0.128%

    No Known Activations