© 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. 48258
    Prev
    Next
    INDEX
    Explanations

    collocations

    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
     ಎರಡು
    0.58
    imli
    0.54
     два
    0.52
    gewood
    0.49
     कॉस्ट
    0.48
    𝙪
    0.48
    ០០
    0.48
     дві
    0.46
     giornal
    0.46
    rology
    0.46
    POSITIVE LOGITS
    ادم
    0.49
    PAGE
    0.42
     AB
    0.41
     cultivars
    0.41
     bebas
    0.41
     $.
    0.41
    Nationality
    0.41
     puissance
    0.40
     alttext
    0.39
     kB
    0.39
    Activations Density 0.001%

    No Known Activations