© 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. 38724
    Prev
    Next
    INDEX
    Explanations

    maintain, respond, describe, outline

    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
    Hive
    0.48
     местах
    0.44
     Soto
    0.43
     keer
    0.41
     balanceOf
    0.41
    ම
    0.41
     marginBottom
    0.41
     कौशिक
    0.41
    град
    0.41
     Vaux
    0.41
    POSITIVE LOGITS
     הת
    0.50
     dissol
    0.47
    どう
    0.45
    இய
    0.45
    ncoder
    0.44
    hea
    0.42
    Investigation
    0.42
    ح
    0.40
    قي
    0.40
    rimi
    0.40
    Activations Density 0.003%

    No Known Activations