© 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. 30542
    Prev
    Next
    INDEX
    Explanations

    selection and filtering

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

    La Candelaria Walking Tour

    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
     You
    0.56
    on
    0.53
     Law
    0.52
     Occidental
    0.51
     Made
    0.50
    G
    0.49
     on
    0.49
     Who
    0.48
     Curl
    0.48
     Kimberly
    0.47
    POSITIVE LOGITS
     계획
    0.55
     주요
    0.49
    assays
    0.48
     العراق
    0.48
    <unused70>
    0.46
    لعاب
    0.46
    ાવો
    0.46
    jskich
    0.45
    旲
    0.45
    elems
    0.45
    Activations Density 0.001%

    No Known Activations