© 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. 14474
    Prev
    Next
    INDEX
    Explanations

    code execution

    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
     servidores
    0.75
    ('./
    0.74
     servidor
    0.74
     서버
    0.72
     Laravel
    0.71
     слуша
    0.71
    ('/
    0.70
     ROUTES
    0.70
     Listening
    0.70
     SERVER
    0.70
    POSITIVE LOGITS
    mailing
    0.58
     bang
    0.57
     catch
    0.57
    冢
    0.56
     sharp
    0.55
     jä
    0.54
    rescue
    0.52
     هاش
    0.52
    catch
    0.52
    UserInput
    0.52
    Activations Density 0.000%

    No Known Activations