© 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. 713
    Prev
    Next
    INDEX
    Explanations

    discussions about the training processes of large transformer models.

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

    breakdown 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
     are
    0.28
     
    0.20
     (
    0.20
     (!
    0.19
     binoculars
    0.19
    実際に
    0.19
    is
    0.19
     the
    0.18
    \
    0.18
    mselves
    0.18
    POSITIVE LOGITS
     для
    0.32
    для
    0.31
     whereby
    0.30
     जिसने
    0.30
     რომელიც
    0.29
     برای
    0.27
    ของการ
    0.26
     котором
    0.26
     untuk
    0.25
     который
    0.25
    Activations Density 1.939%

    No Known Activations