© 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. 88916
    Prev
    Next
    INDEX
    Explanations

    as well

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

    factors, needs, subscriber, shard

    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
     ძ
    0.47
     সহজেই
    0.47
    icians
    0.46
    ampur
    0.46
    Info
    0.43
    ahid
    0.43
    利用
    0.43
    实时
    0.43
     birbir
    0.43
    Util
    0.43
    POSITIVE LOGITS
     Gibbons
    0.46
    僮
    0.46
     APPENDIX
    0.44
    年纪
    0.44
     Iman
    0.43
     Functional
    0.42
     fürs
    0.42
    ناسب
    0.41
     MNRAS
    0.41
     mögliche
    0.41
    Activations Density 0.000%

    No Known Activations