© 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. 53959
    Prev
    Next
    INDEX
    Explanations

    future/future

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

    compound surnames and finances

    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
    手
    0.42
    ع
    0.40
    धनों
    0.40
    ")));
    0.39
    大阪
    0.39
    drain
    0.39
     drains
    0.38
     hostile
    0.38
     باعث
    0.38
     darunter
    0.38
    POSITIVE LOGITS
     будущего
    0.47
     உள்ப
    0.46
     KEYUP
    0.42
     脱
    0.42
     SECURITY
    0.42
     캠
    0.42
     Augustine
    0.41
     ভবিষ্যৎ
    0.41
     futura
    0.41
     కాని
    0.41
    Activations Density 0.000%

    No Known Activations