© 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. 11552
    Prev
    Next
    INDEX
    Explanations

    index followed by book

    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
     対策
    -1.26
    の概要
    -1.20
    を試
    -1.19
    zdo
    -1.14
    Źródło
    -1.13
    に行ってきました
    -1.09
    زیک
    -1.07
    Nazwa
    -1.07
    wię
    -1.05
    Ży
    -1.05
    POSITIVE LOGITS
    r
    1.43
    l
    1.36
    on
    1.36
    u
    1.35
    i
    1.34
     mentre
    1.34
    o
    1.34
    is
    1.33
    g
    1.31
    h
    1.30
    Activations Density 0.011%

    No Known Activations