© 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. 110156
    Prev
    Next
    INDEX
    Explanations

    unique language, LL, shattering, timing

    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
     Beaumont
    0.51
     shouldUse
    0.45
    ة
    0.45
    ன்
    0.44
     выпущен
    0.43
     Boley
    0.43
    న్
    0.43
     తీసుకు
    0.43
     boldly
    0.42
     motocicleta
    0.42
    POSITIVE LOGITS
    ers
    0.49
    icted
    0.47
    抔
    0.47
    수로
    0.46
     იგი
    0.44
    杩
    0.44
    者に
    0.44
    立场
    0.44
    鳃
    0.44
     고려
    0.43
    Activations Density 0.001%

    No Known Activations