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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127290
    Prev
    Next
    INDEX
    Explanations

    serious negative consequences

    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
    ㉕
    -1.91
    bricas
    -1.74
          
    -1.69
     cesse
    -1.69
     sorrow
    -1.68
    iffance
    -1.66
    姌
    -1.61
     damned
    -1.61
     divinely
    -1.56
     schicken
    -1.55
    POSITIVE LOGITS
    );
    2.03
    .
    2.00
     dėl
    1.71
    ization
    1.60
     hjelp
    1.59
    ...");
    1.54
     and
    1.52
     principally
    1.51
    the
    1.48
    꾀
    1.47
    Activations Density 0.010%

    No Known Activations