© 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. 128656
    Prev
    Next
    INDEX
    Explanations

    selection of, mustard mixture, polling, fees, role

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

    acting as a model

    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
    7
    0.51
     czasie
    0.49
     unsolved
    0.48
    ۶
    0.46
    can
    0.46
    6
    0.45
     miesią
    0.45
    kannten
    0.45
     unik
    0.44
     ustan
    0.44
    POSITIVE LOGITS
     rivulet
    0.43
    쯜
    0.43
    ^{*}$-
    0.41
     Lotto
    0.41
     প্রাই
    0.41
    ⓔ
    0.41
     Kline
    0.40
    立马
    0.40
    🆒
    0.40
    ဘူး
    0.40
    Activations Density 0.001%

    No Known Activations