© 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. 6557
    Prev
    Next
    INDEX
    Explanations

    `.com email addresses

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

    term that

    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
     แต่
    0.56
     सीधे
    0.55
     उपयोगकर्ता
    0.50
     ácido
    0.48
     Doğ
    0.48
     लेकिन
    0.47
     옆
    0.47
     Тогда
    0.47
     东
    0.47
     kullanıcı
    0.46
    POSITIVE LOGITS
    用了
    0.44
     glazing
    0.44
    λον
    0.43
    準
    0.41
     valuation
    0.41
    感が
    0.41
     INDIANA
    0.41
    ertung
    0.41
    LIED
    0.41
    isierung
    0.41
    Activations Density 0.000%

    No Known Activations