© 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. 99416
    Prev
    Next
    INDEX
    Explanations

    No, rest, kite, or call

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

    short dialogue

    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
    Я
    0.52
    ד
    0.52
    しました
    0.50
    ס
    0.48
    צ
    0.47
    ה
    0.46
    挖
    0.46
    Г
    0.46
    ₹
    0.46
     QUE
    0.45
    POSITIVE LOGITS
     prudence
    0.46
     Botan
    0.45
    phenylsulfanyl
    0.45
    ubarb
    0.45
     เฮ
    0.44
     விரி
    0.43
     Algonquin
    0.43
     紅
    0.43
    ニーズ
    0.42
     Bites
    0.42
    Activations Density 0.000%

    No Known Activations