© 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. 25873
    Prev
    Next
    INDEX
    Explanations

    candidate, COP, report, EAS, discovered

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

    consequences and benefits

    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
     l
    0.55
     by
    0.54
     o
    0.52
    ing
    0.52
     *
    0.52
     ri
    0.52
     so
    0.50
     ip
    0.50
    ativ
    0.50
     qua
    0.50
    POSITIVE LOGITS
    ediakan
    0.52
     Strengthen
    0.52
     క్
    0.50
     padassa
    0.50
     什么
    0.49
    糇
    0.49
    鸪
    0.48
     Illustrated
    0.48
     шкі
    0.48
    េទ
    0.47
    Activations Density 0.000%

    No Known Activations