© 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. 17184
    Prev
    Next
    INDEX
    Explanations

    German and English words

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

    YouTube channels and system design

    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
    뱀
    0.51
    잎
    0.49
    梵
    0.47
    ゲーム
    0.47
     inqu
    0.47
    면
    0.47
     गेम्स
    0.46
    점에서
    0.46
     کلب
    0.45
     صہیونیوں
    0.45
    POSITIVE LOGITS
     runde
    0.53
     more
    0.52
     более
    0.51
     lich
    0.49
    runde
    0.49
     hund
    0.48
    ↵↵↵
    0.47
    more
    0.47
     caravan
    0.47
     rumble
    0.46
    Activations Density 0.000%

    No Known Activations