© 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. 112240
    Prev
    Next
    INDEX
    Explanations

    living and active or powerful

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

    getting noticed

    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
     យើង
    0.50
    你能
    0.49
    妣
    0.48
     cómo
    0.48
    धारणा
    0.48
     observación
    0.47
     μπορού
    0.46
     disprove
    0.46
    ሖ
    0.46
     حاول
    0.46
    POSITIVE LOGITS
     newly
    0.45
     Newly
    0.43
     Oracle
    0.42
     compelling
    0.40
     providing
    0.40
    พลิ
    0.38
     delightfully
    0.38
     gems
    0.38
    த்தம்
    0.38
     वादा
    0.38
    Activations Density 0.000%

    No Known Activations