© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 1249
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to computer networking and data management.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    one of

    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
     อยู่
    0.28
    since
    0.27
    re
    0.27
    ⏰
    0.26
     pokud
    0.25
    😯
    0.25
    🚮
    0.25
     를
    0.24
    hyth
    0.24
    ามารถ
    0.24
    POSITIVE LOGITS
    ва
    0.33
    н
    0.31
     of
    0.30
     главных
    0.30
     contender
    0.29
     important
    0.29
    жды
    0.29
     exemplar
    0.29
     one
    0.28
     peculiar
    0.28
    Activations Density 0.424%

    No Known Activations