© 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. 4124
    Prev
    Next
    INDEX
    Explanations

    transparency and openness

    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
     lager
    2.22
     sporadically
    2.05
     borderline
    2.04
     specializing
    2.03
     Lager
    1.98
     sparsely
    1.93
     거기
    1.93
     Kim
    1.92
     USD
    1.90
     뭐
    1.90
    POSITIVE LOGITS
    वेळी
    2.14
    łoży
    2.08
    దిక
    2.05
    >}</
    2.03
    സ്തു
    2.00
    été
    1.94
    ッシング
    1.93
    jib
    1.93
    addContainerGap
    1.92
    idmat
    1.88
    Activations Density 0.011%

    No Known Activations