© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69906
    Prev
    Next
    INDEX
    Explanations

    Networking protocols and classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    commentaire
    1.74
     pastes
    1.73
    ukka
    1.72
    ussion
    1.71
     cadence
    1.70
    curvature
    1.70
     analyte
    1.68
    季
    1.67
    ased
    1.64
     reagents
    1.64
    POSITIVE LOGITS
     infrac
    1.21
    hitva
    1.20
     poursu
    1.17
     forhold
    1.15
     właści
    1.15
    偲
    1.14
    인의
    1.13
     kunne
    1.12
     côn
    1.11
     conex
    1.10
    Activations Density 0.001%

    No Known Activations