© 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. 79351
    Prev
    Next
    INDEX
    Explanations

    defining or explaining concepts

    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
    c
    0.50
    are
    0.49
    down
    0.49
     whereupon
    0.48
    es
    0.47
    gram
    0.47
    l
    0.47
    dom
    0.45
     ខ
    0.45
    downloader
    0.45
    POSITIVE LOGITS
    Deps
    0.49
    Diag
    0.47
    னர்
    0.45
    DY
    0.44
     বক্তব
    0.44
    ن
    0.43
    ники
    0.42
    НЫ
    0.42
    鎂
    0.42
     더욱
    0.42
    Activations Density 0.007%

    No Known Activations