© 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. 2786
    Prev
    Next
    INDEX
    Explanations

    requires subscription

    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
    tub
    1.45
    ies
    1.38
    iat
    1.37
    oo
    1.28
    oom
    1.21
    h
    1.21
    ir
    1.19
    ev
    1.19
    nt
    1.19
    tl
    1.19
    POSITIVE LOGITS
     hỗ
    2.75
     Hinweise
    2.48
     takže
    2.43
     khả
    2.35
     以及
    2.24
     특징
    2.24
     Để
    2.23
     Chất
    2.23
     vigente
    2.21
     지원
    2.21
    Activations Density 0.078%

    No Known Activations