© 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. 139433
    Prev
    Next
    INDEX
    Explanations

    equates to, roughly, nice set, twenty years, families of

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

    Volumetric Indicators

    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
    යේ
    0.54
     Pourquoi
    0.47
    患者
    0.47
    隘
    0.46
     بنی
    0.45
    を発
    0.45
     στους
    0.44
    工作的
    0.44
    再加上
    0.44
    ;
    0.43
    POSITIVE LOGITS
    ล
    0.49
    бах
    0.49
    rcl
    0.48
    п
    0.45
    SPL
    0.44
    ঁজ
    0.44
    фф
    0.44
    ീല
    0.43
    嬉
    0.42
    Expiry
    0.42
    Activations Density 0.001%

    No Known Activations