© 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. 4935
    Prev
    Next
    INDEX
    Explanations

    entities' roles or actions

    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
    sp
    0.45
    as
    0.42
    your
    0.42
    ที่คุณ
    0.41
    i
    0.41
    id
    0.40
     your
    0.40
    og
    0.40
    on
    0.39
    y
    0.39
    POSITIVE LOGITS
     számára
    0.50
     participation
    0.49
     சார்பில்
    0.47
     પાસે
    0.44
     didik
    0.44
     بالأ
    0.42
     atividades
    0.42
    にとって
    0.41
     toekom
    0.41
     участие
    0.40
    Activations Density 0.140%

    No Known Activations