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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34270
    Prev
    Next
    INDEX
    Explanations

    Bookmark the permalink

    np_acts-logits-general · gemini-2.5-flash-lite

    prioritizing change and strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     is
    0.40
     commercial
    0.39
    ’
    0.38
     beverage
    0.38
     delivers
    0.38
     drove
    0.37
     promotes
    0.36
     had
    0.36
     serves
    0.36
     responsibly
    0.36
    POSITIVE LOGITS
    枤
    0.47
     삼각형
    0.46
     topLeft
    0.45
     विभक्ति
    0.45
    กฎ
    0.44
     규칙
    0.44
     왼쪽
    0.43
     Variablen
    0.43
     변화
    0.43
     분포
    0.42
    Activations Density 0.001%

    No Known Activations