© 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. 12886
    Prev
    Next
    INDEX
    Explanations

    isn't and aren't

    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
     ph
    2.31
    tanto
    2.22
    larda
    2.20
    lia
    2.19
     Qu
    2.18
    ment
    2.12
    mente
    2.06
    𝘨
    1.97
     Ph
    1.97
    ded
    1.96
    POSITIVE LOGITS
    噌
    2.69
    𝙧
    2.69
    𝙣
    2.67
    𝙚
    2.65
    রান
    2.62
    𝙖
    2.57
    励
    2.55
    olesale
    2.53
    𝙞
    2.47
    insuku
    2.46
    Activations Density 0.060%

    No Known Activations