© 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. 149661
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    driving for dollars

    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
     Mant
    0.48
    mant
    0.47
    Mant
    0.47
    тріш
    0.46
    ço
    0.44
    قط
    0.44
     Chemistry
    0.44
    ,
    0.44
     show
    0.44
     chemistry
    0.44
    POSITIVE LOGITS
    atok
    0.52
     madrugada
    0.50
    adek
    0.48
    adins
    0.46
     menentukan
    0.46
     cucumbers
    0.46
     রাতের
    0.46
     僕
    0.45
    オープ
    0.45
    adoop
    0.45
    Activations Density 0.000%

    No Known Activations