© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12937
    Prev
    Next
    INDEX
    Explanations

    As of today, November 2, 2023

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     any
    1.62
     some
    1.46
     another
    1.27
     plenty
    1.27
     these
    1.26
    بعض
    1.24
     بعض
    1.22
     many
    1.22
     a
    1.19
    stehen
    1.18
    POSITIVE LOGITS
    PUT
    1.67
     Motto
    1.49
     motto
    1.40
    POSAL
    1.38
    假设
    1.37
    榎
    1.37
    ocado
    1.35
     proviso
    1.34
    会の
    1.33
    シューズ
    1.31
    Activations Density 0.073%

    No Known Activations