© 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. 201824
    Prev
    Next
    INDEX
    Explanations

    robot riding on a horse

    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
    ப
    0.50
    W
    0.50
    У
    0.46
    '
    0.46
    Under
    0.44
     Kupp
    0.43
    Ві
    0.43
    ປ
    0.42
    pointer
    0.41
    В
    0.41
    POSITIVE LOGITS
    quinox
    0.50
    égation
    0.49
     casserole
    0.47
    idal
    0.47
    giveness
    0.46
     campagna
    0.46
    োল
    0.46
    idot
    0.45
    ición
    0.45
    omsday
    0.45
    Activations Density 0.002%

    No Known Activations