© 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. 13203
    Prev
    Next
    INDEX
    Explanations

    confidence, agency, like, shows, do

    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
    groovy
    1.40
    ><%=
    1.39
    SIZE
    1.36
     अवैध
    1.33
     מו
    1.32
     חלק
    1.29
    TeXAtom
    1.28
    sizeof
    1.28
    Mfg
    1.27
    ͟
    1.27
    POSITIVE LOGITS
    खास्त
    1.23
    agher
    1.11
    iende
    1.08
     geval
    1.08
    reonine
    1.05
    aseña
    1.03
     primaria
    1.03
    endum
    1.03
    계를
    1.03
    řich
    1.02
    Activations Density 0.000%

    No Known Activations