© 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. 143329
    Prev
    Next
    INDEX
    Explanations

    also conjunctions or linking words

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

    clarity and specification

    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
     વર્
    0.50
     Пу
    0.49
     Сури
    0.48
     кі
    0.47
     мою
    0.47
     т
    0.46
     Ку
    0.46
     соци
    0.46
     Бу
    0.46
     стек
    0.45
    POSITIVE LOGITS
     invester
    0.49
    起こ
    0.44
     ERROR
    0.44
    क्रो
    0.44
    It
    0.44
    प्रेम
    0.41
    कर्षण
    0.41
    ڳ
    0.41
    Lähteet
    0.41
    โยชน์
    0.40
    Activations Density 0.001%

    No Known Activations