© 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. 201429
    Prev
    Next
    INDEX
    Explanations

    trophies and models

    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
     occasioned
    0.49
     fragmentary
    0.47
     چنان
    0.45
     mixts
    0.44
    囡
    0.44
     unpacked
    0.44
     إِن
    0.43
     partitioned
    0.43
     embroidered
    0.43
     Contributions
    0.42
    POSITIVE LOGITS
    at
    0.46
    íp
    0.45
    rich
    0.45
    夺
    0.44
    abhar
    0.43
    behör
    0.42
    eb
    0.41
    err
    0.41
    碼
    0.41
    ileg
    0.41
    Activations Density 0.000%

    No Known Activations