© 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-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1744
    Prev
    Next
    INDEX
    Explanations

    URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    0.97
    вол
    0.86
     that
    0.85
     on
    0.81
    Remember
    0.80
     in
    0.78
     (
    0.77
    0.77
     almost
    0.76
     indirectly
    0.73
    POSITIVE LOGITS
    www
    1.37
     vaksin
    1.32
    nbhost
    1.30
     texto
    1.25
     parametros
    1.24
     vins
    1.23
    또한
    1.22
     menyampaikan
    1.21
     tional
    1.21
     terdiri
    1.19
    Activations Density 0.171%

    No Known Activations