© 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. 149398
    Prev
    Next
    INDEX
    Explanations

    evaporating or vaporizing

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

    years and invasion

    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
    kennt
    0.46
    갑습니다
    0.44
    ርስዎ
    0.44
    颔
    0.44
    كمة
    0.43
    ურთი
    0.43
    我很
    0.42
    금융
    0.42
    柅
    0.42
     फाइनेंशियल
    0.42
    POSITIVE LOGITS
     vapors
    0.51
    ग
    0.43
     abyss
    0.42
     evaporate
    0.42
     vaporization
    0.42
     tah
    0.41
     químicos
    0.40
     temperaturas
    0.40
     suhu
    0.40
     whatnot
    0.40
    Activations Density 0.001%

    No Known Activations