© 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. 120640
    Prev
    Next
    INDEX
    Explanations

    specific technical terms

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

    perfect opposition

    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
    peasants
    0.51
    arlane
    0.49
    ór
    0.48
    u
    0.48
    zad
    0.48
    ≖
    0.47
    其他
    0.46
    ają
    0.46
    ">=
    0.46
     ಹ
    0.46
    POSITIVE LOGITS
     bialgebras
    0.57
     nghi
    0.47
     Compile
    0.47
    GetHeight
    0.47
    фии
    0.46
     unbound
    0.45
    తన
    0.45
     incre
    0.44
    гии
    0.42
     linguagem
    0.42
    Activations Density 0.001%

    No Known Activations