© 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. 106797
    Prev
    Next
    INDEX
    Explanations

    what you need

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

    extracting data, reasons why, device control

    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
     servizio
    0.49
     çevre
    0.49
     சுற்றுச்சூழல்
    0.47
     Í
    0.46
     ciò
    0.45
     уста
    0.45
     ENVIRONMENTAL
    0.44
     सर्वि
    0.43
     сервис
    0.43
     технологі
    0.43
    POSITIVE LOGITS
     rewrite
    0.53
    부터
    0.50
    뜨
    0.48
     संक्रम
    0.47
     চরণ
    0.46
    爱的
    0.46
    ല്ലോ
    0.46
     부터
    0.46
     reprise
    0.45
    르
    0.45
    Activations Density 0.000%

    No Known Activations