© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51007
    Prev
    Next
    INDEX
    Explanations

    or or no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prepara
    0.47
     pekan
    0.42
    Ꮿ
    0.41
     नाराज
    0.39
    ۊ
    0.38
    ষা
    0.38
    tea
    0.38
     stubborn
    0.38
     immobilier
    0.38
     merry
    0.38
    POSITIVE LOGITS
     или
    0.47
    Bracketing
    0.45
     ไม่มี
    0.44
     Presumably
    0.43
     ਜਾਂ
    0.42
     нет
    0.42
     없을
    0.42
     ἢ
    0.42
     брига
    0.41
     مسلم
    0.41
    Activations Density 0.003%

    No Known Activations