© 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. 66105
    Prev
    Next
    INDEX
    Explanations

    number or count following certain words

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

    light / security / awakening / blur

    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
    א
    0.44
    볼
    0.44
    ೊ
    0.42
    ை
    0.41
    osphate
    0.41
    䛊
    0.39
    proble
    0.39
     혹
    0.39
    ㄑ
    0.38
    }-[
    0.38
    POSITIVE LOGITS
     fittest
    0.44
     सीजन
    0.41
    වුන්
    0.41
     massimo
    0.41
     synced
    0.40
     vita
    0.40
     تعداد
    0.40
     releg
    0.39
     Huskies
    0.39
     sayıda
    0.39
    Activations Density 0.001%

    No Known Activations