© 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. 15419
    Prev
    Next
    INDEX
    Explanations

    family terms

    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
    ಂಥ
    0.61
     Gutenberg
    0.59
     요
    0.59
    、『
    0.59
     squarely
    0.59
     posterity
    0.57
    『
    0.57
     Geografia
    0.56
     ภาษา
    0.55
     `
    0.54
    POSITIVE LOGITS
     സുമിത്ര
    0.67
     ta
    0.63
     eyel
    0.61
     වල
    0.59
     সাপোর্ট
    0.59
     വേദിക
    0.59
    elerinin
    0.57
     caracter
    0.56
     වලින්
    0.56
     proposal
    0.55
    Activations Density 0.007%

    No Known Activations