© 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-16K
    7. 7188
    Prev
    Next
    INDEX
    Explanations

    ratings and scales

    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_16k_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
     dint
    0.43
    ρώ
    0.41
    oda
    0.40
    ◡
    0.40
     যতটুকু
    0.39
     いい
    0.39
    oit
    0.38
    砀
    0.38
    どこ
    0.37
    oin
    0.37
    POSITIVE LOGITS
    惑星
    0.45
     superstars
    0.41
    หลาย
    0.40
     ট্র
    0.40
    kreis
    0.39
     sovereignty
    0.38
     क्षेत्रों
    0.37
     इंफॉर्मेशन
    0.36
    ルド
    0.36
     kingdoms
    0.36
    Activations Density 0.066%

    No Known Activations