© 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. 1616
    Prev
    Next
    INDEX
    Explanations

    numerical ranges and measurements

    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
     a
    1.23
     It
    1.18
     it
    1.14
     had
    1.04
     overly
    1.04
     In
    1.03
     all
    1.02
     the
    1.02
     are
    1.01
     ك
    1.00
    POSITIVE LOGITS
     ஆலோச
    1.70
    ッピング
    1.67
     മേഖ
    1.60
     coordinador
    1.58
     secretário
    1.57
     secrétaire
    1.54
    ociazione
    1.54
    udiante
    1.53
     प्रकोष्ठ
    1.50
    呫
    1.50
    Activations Density 0.599%

    No Known Activations