© 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. 685
    Prev
    Next
    INDEX
    Explanations

    technological and legal issues related to online content access.

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

    through, from, or without

    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
     elucidation
    0.23
     depiction
    0.23
     bild
    0.22
    &
    0.22
     gt
    0.22
     Verbindung
    0.22
    gt
    0.21
    *,
    0.21
     regarding
    0.21
     والم
    0.21
    POSITIVE LOGITS
    through
    0.35
     бесплатно
    0.32
    จาก
    0.32
     from
    0.32
     через
    0.32
     without
    0.31
     efficiently
    0.31
     efficacement
    0.31
     through
    0.31
     без
    0.31
    Activations Density 1.136%

    No Known Activations