© 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-262K
    7. 46771
    Prev
    Next
    INDEX
    Explanations

    profile and measurements

    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
    י
    0.52
    К
    0.49
    NA
    0.48
    И
    0.47
    Î
    0.46
    Ciudad
    0.44
    حظ
    0.44
    İŞ
    0.44
    ли
    0.44
     hâ
    0.44
    POSITIVE LOGITS
     sewing
    0.48
     inner
    0.47
    onics
    0.44
     υπάρχ
    0.44
     \|
    0.43
     judging
    0.43
     pausing
    0.43
     Bulgarian
    0.43
     retreating
    0.43
     theses
    0.42
    Activations Density 0.003%

    No Known Activations