© 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
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14772
    Prev
    Next
    INDEX
    Explanations

    venting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ırım
    0.53
    倨
    0.53
     गेहूं
    0.50
     ferrugine
    0.50
     შეუ
    0.49
     awe
    0.49
     ಖರೀ
    0.48
    眄
    0.48
     resale
    0.48
     bege
    0.47
    POSITIVE LOGITS
     venting
    1.98
     vent
    1.90
     vented
    1.79
     vents
    1.74
     cath
    1.65
     Vent
    1.59
     ventil
    1.55
    Vent
    1.49
    vent
    1.42
     outlet
    1.41
    Activations Density 0.123%

    No Known Activations