© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-65K
    7. 1300
    Prev
    Next
    INDEX
    Explanations

    guns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
     huwa
    0.56
    რივი
    0.55
    ઠળ
    0.54
     backgroundImg
    0.54
     Herald
    0.54
    祝
    0.52
     Io
    0.52
     سرحد
    0.51
     Kochubei
    0.50
     Scrolling
    0.49
    POSITIVE LOGITS
    gun
    0.57
     gun
    0.55
    枪
    0.53
     guns
    0.52
    codigo
    0.51
    руют
    0.51
     eivät
    0.50
     एंड
    0.49
     personas
    0.49
    guns
    0.48
    Activations Density 0.000%

    No Known Activations