© 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. 209438
    Prev
    Next
    INDEX
    Explanations

    sunny, and cookie, and

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

    defining steel plate

    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
     جهاز
    0.49
     exemplaire
    0.47
     مخلو
    0.46
    鲲
    0.46
     majest
    0.46
     مليون
    0.46
    ല
    0.45
    Ｍ
    0.45
     działal
    0.44
    гне
    0.44
    POSITIVE LOGITS
    ur
    0.51
    ala
    0.49
    ini
    0.49
    iti
    0.49
    asis
    0.49
    seo
    0.48
    anna
    0.47
    asser
    0.46
    ondi
    0.46
    ava
    0.45
    Activations Density 0.002%

    No Known Activations