© 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. 128479
    Prev
    Next
    INDEX
    Explanations

    static content or user interaction

    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
     compatible
    0.45
    鎖
    0.42
    ンの
    0.42
     cottonseed
    0.41
     subjected
    0.40
     contradicting
    0.40
     incompatible
    0.39
     hypoc
    0.39
    及
    0.39
     conflicting
    0.39
    POSITIVE LOGITS
     vaak
    0.46
    လည်း
    0.46
     வயது
    0.45
     väldigt
    0.45
     ძალიან
    0.44
     ĝi
    0.43
     teknologi
    0.43
     få
    0.43
    人类
    0.43
    द्वानी
    0.43
    Activations Density 0.017%

    No Known Activations