© 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. 40703
    Prev
    Next
    INDEX
    Explanations

    should verb patterns

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

    foreign characters and text

    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
     pouvaient
    0.40
     falamos
    0.40
    ⛔
    0.39
     নিষেধ
    0.38
    ONU
    0.37
    ΝΑ
    0.36
     luas
    0.35
     birthplace
    0.34
     housings
    0.34
    就能
    0.34
    POSITIVE LOGITS
    alph
    0.39
    ুল
    0.39
    橼
    0.39
    äh
    0.38
     suffix
    0.38
    दिल
    0.38
    ヒー
    0.38
     സഹ
    0.37
    ífer
    0.37
    ッカ
    0.37
    Activations Density 0.001%

    No Known Activations