© 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. 11503
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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
    <bos>
    -2.58
    を
    -2.33
    が
    -2.28
    and
    -2.08
    e
    -1.98
    があり
    -1.96
    と
    -1.91
    in
    -1.88
    でしょうね
    -1.87
    がある
    -1.86
    POSITIVE LOGITS
    為に
    2.23
    で見る
    2.23
    の方も
    2.19
    つづく
    2.17
    の方に
    2.14
    の絵
    2.09
    に似
    2.06
    に変更
    2.05
    を買う
    1.99
    ごとの
    1.98
    Activations Density 0.073%

    No Known Activations