© 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. 46899
    Prev
    Next
    INDEX
    Explanations

    describing Gemma and technical/business topics

    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
    ز
    0.62
    ты
    0.61
    ру
    0.58
    ش
    0.57
    ри
    0.56
    rupción
    0.54
    тивы
    0.54
    z
    0.54
    ы
    0.54
    те
    0.53
    POSITIVE LOGITS
     postulated
    0.49
     \
    0.47
     নিম্নলিখিত
    0.46
     αποτέ
    0.44
    REW
    0.44
     συνέχ
    0.44
     hypothesized
    0.44
     ξεκ
    0.43
     όλ
    0.43
     isothermal
    0.42
    Activations Density 0.000%

    No Known Activations