© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12184
    Prev
    Next
    INDEX
    Explanations

    for loop indexing

    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_22/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
     anything
    -1.06
    いろいろ
    -0.98
    Inhalts
    -0.93
     interrom
    -0.91
    补贴
    -0.90
    embal
    -0.88
     roba
    -0.88
     harita
    -0.87
     engel
    -0.87
    色々
    -0.85
    POSITIVE LOGITS
     for
    1.30
     riêng
    0.99
     in
    0.99
    squareup
    0.94
     separate
    0.94
     with
    0.92
     at
    0.87
    氏は
    0.87
     distinct
    0.87
    specific
    0.86
    Activations Density 0.007%

    No Known Activations