© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82402
    Prev
    Next
    INDEX
    Explanations

    service ID count

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ހ
    0.54
     semua
    0.52
    N
    0.50
    t
    0.49
    Т
    0.49
    Why
    0.49
     Semua
    0.47
    По
    0.47
    小
    0.46
    Е
    0.46
    POSITIVE LOGITS
    绎
    0.46
     ₹
    0.45
    ediaan
    0.45
     stalemate
    0.44
    şik
    0.43
     vời
    0.43
    시켜
    0.43
     jīn
    0.42
     reservar
    0.42
     Reserved
    0.42
    Activations Density 0.003%

    No Known Activations