© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2774
    Prev
    Next
    INDEX
    Explanations

    some [various concepts]

    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_7_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
     ২৮
    1.98
     ২৭
    1.87
     ২৬
    1.87
     керів
    1.86
    abee
    1.86
     ১৮
    1.84
    小屋
    1.82
    Chairman
    1.81
     Ά
    1.78
     middlewares
    1.77
    POSITIVE LOGITS
     exposure
    1.47
     typing
    1.45
    ed
    1.35
     sensitivity
    1.31
     തവണ
    1.30
     prop
    1.30
    <bos>
    1.27
     exp
    1.24
     elastic
    1.19
     exposures
    1.19
    Activations Density 0.158%

    No Known Activations