© 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. 241574
    Prev
    Next
    INDEX
    Explanations

    ropes courses, add on, nice wee

    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
    䔉
    0.48
    Blitz
    0.47
    顐
    0.45
    Tact
    0.45
    лур
    0.44
    槑
    0.44
     تومان
    0.44
    栤
    0.44
     Blitz
    0.43
    IsResolver
    0.43
    POSITIVE LOGITS
    NA
    0.53
    உ
    0.48
    encoding
    0.47
    NV
    0.46
    クサ
    0.44
    ua
    0.44
    ').
    0.44
    (
    0.43
    サ
    0.43
    0.43
    Activations Density 0.001%

    No Known Activations