© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 173448
    Prev
    Next
    INDEX
    Explanations

    foreign language fragments and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    specific actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    џ
    0.53
     BAM
    0.49
    وا
    0.46
     acts
    0.46
    اعات
    0.46
     pitiful
    0.45
    ش
    0.44
     on
    0.43
     Acts
    0.43
    이기
    0.43
    POSITIVE LOGITS
    aient
    0.51
     effiz
    0.49
    ltk
    0.49
     chiropractic
    0.49
     चमक
    0.48
     ثانيه
    0.48
     रोम
    0.47
     machte
    0.47
    beyblade
    0.47
     велоси
    0.47
    Activations Density 0.000%

    No Known Activations