© 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. 137770
    Prev
    Next
    INDEX
    Explanations

    liability, small, question marks, punctuation

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

    states of being or conditions

    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
     bastante
    0.48
     tienen
    0.47
     oxyd
    0.47
     acto
    0.47
    ヌ
    0.46
    >
    0.46
     akt
    0.46
     aquell
    0.45
    «.
    0.45
    ＞
    0.45
    POSITIVE LOGITS
    trp
    0.56
    shp
    0.48
    ugia
    0.47
     turbine
    0.46
    ogia
    0.46
    rene
    0.45
    leme
    0.45
     Homeland
    0.44
    spark
    0.44
     BG
    0.44
    Activations Density 0.001%

    No Known Activations