© 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. 204109
    Prev
    Next
    INDEX
    Explanations

    legal reasons

    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
    狡
    0.57
    与
    0.51
     Técn
    0.49
     Алек
    0.47
     Intelig
    0.47
    象
    0.47
    岗位
    0.46
     Veamos
    0.46
     Geheim
    0.45
     Composer
    0.45
    POSITIVE LOGITS
    ano
    0.56
    zhou
    0.49
    uses
    0.49
    ro
    0.48
    អនុ
    0.47
     eyeballs
    0.47
    ao
    0.47
    ppm
    0.47
    oler
    0.46
    è
    0.46
    Activations Density 0.000%

    No Known Activations