© 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. 77586
    Prev
    Next
    INDEX
    Explanations

    given an, stays on, sender's, ridiculous game, cleaning techniques

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

    big names

    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
     প্রশ্ন
    0.53
    stride
    0.52
    proposed
    0.50
     sorular
    0.48
    يته
    0.48
     distinta
    0.48
     մ
    0.47
     ちゃう
    0.47
     উদ্ভাব
    0.47
    fourths
    0.46
    POSITIVE LOGITS
    고
    0.51
    잿
    0.48
     Egg
    0.46
     accounts
    0.46
    Author
    0.46
     Manuscripts
    0.45
    їн
    0.44
    ทำ
    0.44
     Ads
    0.44
     on
    0.44
    Activations Density 0.000%

    No Known Activations