© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 14681
    Prev
    Next
    INDEX
    Explanations

    places

    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
    Essex
    0.67
     Essex
    0.64
     Alameda
    0.59
     Hudson
    0.58
     Serpent
    0.57
    Hudson
    0.57
     Norwalk
    0.56
    荻
    0.56
     serpent
    0.55
     Hampshire
    0.53
    POSITIVE LOGITS
     Syracuse
    1.26
     Syr
    0.88
     CNY
    0.83
     Cicero
    0.75
     Liverpool
    0.75
    Liverpool
    0.75
     Carrier
    0.69
     Crou
    0.69
     लखनऊ
    0.66
     Fayetteville
    0.64
    Activations Density 0.024%

    No Known Activations