© 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. 77635
    Prev
    Next
    INDEX
    Explanations

    place folders arbitrator

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

    third-party developers, issues, solstice, server

    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
     INTO
    0.52
     musée
    0.52
    ও
    0.48
     canad
    0.46
    ographique
    0.46
     преми
    0.45
     maîtrise
    0.45
     conclusion
    0.43
     CONCLUSION
    0.43
    ㈜
    0.42
    POSITIVE LOGITS
    ell
    0.55
    alo
    0.51
    entas
    0.48
    icked
    0.47
    िलो
    0.46
    ین
    0.46
     overweight
    0.46
    olip
    0.46
    лии
    0.45
    icc
    0.44
    Activations Density 0.000%

    No Known Activations