© 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-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1188
    Prev
    Next
    INDEX
    Explanations

    logging time format

    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
     (+
    1.16
     so
    1.14
     NT
    1.13
     conform
    1.12
     co
    1.09
     ins
    1.08
     catch
    1.06
     (-
    1.06
     (
    1.06
     ND
    1.06
    POSITIVE LOGITS
     dirinya
    1.69
    ಎಸ್
    1.55
    ധ്യ
    1.47
     couro
    1.45
    ے
    1.44
     cadeira
    1.42
    contador
    1.42
     wajah
    1.42
     figli
    1.41
     dítě
    1.40
    Activations Density 0.000%

    No Known Activations