© 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. 143368
    Prev
    Next
    INDEX
    Explanations

    loans, federal, color, monitor, higher, very

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

    computer or device

    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
    য়ং
    0.55
    ্যাথ
    0.50
     rollers
    0.48
     Β
    0.48
     സ്കൂ
    0.47
    squre
    0.46
     interacting
    0.46
     Ι
    0.46
    <bbox>
    0.45
    軽量
    0.45
    POSITIVE LOGITS
    OL
    0.45
     brou
    0.45
    frage
    0.43
     ander
    0.42
    0.42
    اويه
    0.41
     Jesse
    0.41
     pán
    0.41
     другом
    0.40
    omn
    0.40
    Activations Density 0.000%

    No Known Activations