© 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. 2734
    Prev
    Next
    INDEX
    Explanations

    government actions and policies

    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
    s
    1.89
    er
    1.72
    т
    1.56
     Offices
    1.53
     Political
    1.51
    c
    1.48
    e
    1.43
    Political
    1.42
    ी
    1.42
    Municipal
    1.40
    POSITIVE LOGITS
     leverage
    1.73
     streng
    1.71
     vattum
    1.63
     eigenvalues
    1.63
    ື້ນ
    1.62
    верну
    1.62
     wavefunction
    1.58
     flexDirection
    1.57
    LAGS
    1.56
    gehend
    1.56
    Activations Density 0.084%

    No Known Activations