© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1657
    Prev
    Next
    INDEX
    Explanations

    variable assignments and initializations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     innym
    0.88
     legitim
    0.88
    맇
    0.87
     sodass
    0.84
     tā
    0.83
     repent
    0.83
     entsprechenden
    0.82
     AMPL
    0.80
     substantive
    0.79
     GIVE
    0.78
    POSITIVE LOGITS
    agem
    1.05
     =
    1.02
    Г
    1.01
    さんは
    0.97
    io
    0.94
    iflora
    0.92
    opolymers
    0.91
    ijn
    0.91
    agens
    0.90
    was
    0.90
    Activations Density 0.023%

    No Known Activations