© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59553
    Prev
    Next
    INDEX
    Explanations

    civil rights, justice, Holocaust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {
    -2.38
     Why
    -1.92
    たしか
    -1.90
    Why
    -1.89
    To
    -1.85
    他对
    -1.83
    '
    -1.81
    );
    -1.78
    他已经
    -1.70
     and
    -1.68
    POSITIVE LOGITS
     brug
    2.13
     spazi
    2.13
     klarer
    2.09
     biblia
    2.09
     were
    2.05
    ￨
    2.05
    ㌧
    2.03
     essentielle
    2.02
    бурге
    1.98
     famí
    1.98
    Activations Density 0.003%

    No Known Activations