© 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. 151285
    Prev
    Next
    INDEX
    Explanations

    words followed by specific words

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

    covering how to become understanding

    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
     as
    0.47
     بھائی
    0.46
     a
    0.42
     сайті
    0.42
    ',[
    0.41
     one
    0.40
     một
    0.40
     Destroyer
    0.40
     одного
    0.39
     पड़ोसी
    0.39
    POSITIVE LOGITS
     nerada
    0.46
     olha
    0.43
     stále
    0.42
    ካከል
    0.42
    ಡುವುದ
    0.42
    Джек
    0.42
    なし
    0.41
    slateg
    0.40
     акчага
    0.40
    軼
    0.40
    Activations Density 0.001%

    No Known Activations