© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20013
    Prev
    Next
    INDEX
    Explanations

    in order to

    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_65k_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
    ن
    0.86
    ،
    0.80
    1
    0.74
    ン
    0.71
    و
    0.70
    v
    0.69
    ၊
    0.68
    4
    0.68
    ম
    0.68
    、
    0.67
    POSITIVE LOGITS
     to
    0.82
    to
    0.77
    phalodes
    0.61
    lo
    0.57
    ера
    0.54
    ैट
    0.54
    iski
    0.54
    ahankan
    0.54
    ugian
    0.54
    toMatch
    0.54
    Activations Density 0.019%

    No Known Activations