© 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. 41590
    Prev
    Next
    INDEX
    Explanations

    strategies may, grow B, displaying, hi, talking about, child from, 1 9

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

    financial percentage

    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
    с
    0.49
     થઇ
    0.48
     最近
    0.47
    фан
    0.47
     он
    0.47
    RIBUTE
    0.46
    黾
    0.46
    蒉
    0.46
     它
    0.46
    扆
    0.45
    POSITIVE LOGITS
     financière
    0.46
     illuminating
    0.44
     incomes
    0.44
     displaying
    0.43
     celebrities
    0.43
     illuminated
    0.42
     pamię
    0.42
     IDs
    0.42
     vegans
    0.42
     maintaining
    0.41
    Activations Density 0.000%

    No Known Activations