© 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. 2784
    Prev
    Next
    INDEX
    Explanations

    threat of or to

    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
    پوینت
    2.62
    ździe
    2.58
    oader
    2.46
    <bos>
    2.43
     miejsc
    2.42
    ました
    2.41
    DataMat
    2.36
    erical
    2.36
     kojem
    2.33
    uvo
    2.33
    POSITIVE LOGITS
    ra
    2.55
     tor
    2.54
    CHARACTER
    2.49
    АК
    2.31
     maya
    2.28
    𝒶
    2.27
    recon
    2.23
    ia
    2.20
    soff
    2.18
     constat
    2.15
    Activations Density 0.044%

    No Known Activations