© 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. 90728
    Prev
    Next
    INDEX
    Explanations

    hidden sugars

    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
    er
    0.41
    ด
    0.41
     dovrà
    0.40
     posits
    0.40
     כבר
    0.40
     imitating
    0.39
     घेणे
    0.39
     באי
    0.39
     paramagnetic
    0.39
    賀
    0.39
    POSITIVE LOGITS
    tracking
    0.47
    swith
    0.46
     műkö
    0.46
    反复
    0.44
    σεις
    0.44
    tuple
    0.44
     通过
    0.43
     Tide
    0.43
    ກັບ
    0.42
     Tuck
    0.42
    Activations Density 0.009%

    No Known Activations