© 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. 10-GEMMASCOPE-RES-131K
    7. 729
    Prev
    Next
    INDEX
    Explanations

    diuretic, DPI

    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_10/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
    2
    -4.31
    1
    -3.84
    d
    -3.36
    8
    -3.33
    3
    -3.23
    if
    -3.22
    as
    -3.19
    7
    -3.16
    5
    -3.16
    6
    -3.03
    POSITIVE LOGITS
    汌
    2.47
     ktoré
    2.22
    犼
    2.17
     mexicano
    2.14
    ギフト
    2.14
    🍿
    2.11
    YMS
    2.08
     membentuk
    2.08
    可以说
    2.06
    孥
    2.05
    Activations Density 0.006%

    No Known Activations