© 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-262K
    7. 18102
    Prev
    Next
    INDEX
    Explanations

    routing, directing, and referrals

    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_262k_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
    llllllll
    0.40
    acup
    0.38
    resign
    0.38
    icing
    0.37
     বিদ্রোহীদের
    0.36
    )\$(
    0.36
    iso
    0.35
    撤
    0.35
    Latitude
    0.35
    jam
    0.34
    POSITIVE LOGITS
     forwarded
    0.64
     forwarding
    0.63
     referral
    0.57
     дальше
    0.56
    適切な
    0.55
    交给
    0.55
     redirect
    0.55
     dispatch
    0.55
     Referral
    0.55
     directing
    0.54
    Activations Density 0.169%

    No Known Activations