© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14116
    Prev
    Next
    INDEX
    Explanations

    Link

    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
     True
    0.57
     true
    0.55
    True
    0.55
    False
    0.54
    s
    0.54
    brak
    0.53
     Waves
    0.53
     Approaches
    0.53
     Abel
    0.52
     брак
    0.52
    POSITIVE LOGITS
    🔗
    0.88
    ages
    0.85
    age
    0.81
     unlink
    0.78
     링크
    0.76
    unlink
    0.72
     klikken
    0.72
    指向
    0.70
     لنک
    0.70
    oping
    0.68
    Activations Density 0.037%

    No Known Activations