© 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-65K
    7. 56777
    Prev
    Next
    INDEX
    Explanations

    defined tasks and characteristics

    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_65k_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
     drog
    0.46
     Mous
    0.44
     SSA
    0.44
     weeds
    0.42
     lij
    0.42
    쟁
    0.41
    лё
    0.41
     сада
    0.41
     sheds
    0.40
    x
    0.40
    POSITIVE LOGITS
    特徴
    0.61
     scoperta
    0.55
     financement
    0.50
     গবেষণা
    0.50
     hypoxia
    0.49
     proteína
    0.49
     leukocytes
    0.48
     rétréci
    0.48
     खतरा
    0.47
    Características
    0.47
    Activations Density 0.005%

    No Known Activations