© 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. 66320
    Prev
    Next
    INDEX
    Explanations

    special connections and stories

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

    dualism, but contrast

    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
    s
    0.51
    xin
    0.50
    𝑠
    0.49
    ウェイ
    0.47
    caret
    0.46
     کولی
    0.45
    オプション
    0.45
    チップ
    0.43
    User
    0.43
    黎
    0.43
    POSITIVE LOGITS
     entwick
    0.54
     schwierig
    0.54
     ottenere
    0.52
     acho
    0.49
     ache
    0.48
    стів
    0.48
    elle
    0.47
     chamb
    0.47
     desenvolv
    0.47
    isten
    0.47
    Activations Density 0.000%

    No Known Activations