© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53875
    Prev
    Next
    INDEX
    Explanations

    grain, how, sauce, rate, mitigation

    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
     divaricatis
    0.54
    बंधनाच्या
    0.51
    ֮
    0.51
    𝘀
    0.50
    󠁴
    0.50
     Gór
    0.49
    ным
    0.49
     அறிவி
    0.49
    valho
    0.46
    ₁.
    0.46
    POSITIVE LOGITS
    يت
    0.46
    時間
    0.44
     كس
    0.44
    เวลา
    0.43
     volunteer
    0.42
    بيت
    0.42
    豐
    0.41
    rook
    0.41
    丰
    0.41
    Las
    0.41
    Activations Density 0.002%

    No Known Activations