© 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. 231435
    Prev
    Next
    INDEX
    Explanations

    property rates EUR

    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
     Eldorado
    0.47
     '';
    0.47
     रिकार्ड
    0.46
     সামগ্র
    0.45
     vermiş
    0.45
     रक्तदान
    0.44
     clasific
    0.43
    اکي
    0.42
    ;|
    0.42
     Iti
    0.42
    POSITIVE LOGITS
    Bon
    0.52
    ING
    0.45
     অপেক্ষ
    0.45
     해당
    0.43
    意外
    0.43
    veux
    0.43
    홈
    0.43
    вав
    0.42
     жени
    0.42
    연출
    0.41
    Activations Density 0.001%

    No Known Activations