© 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. 34-GEMMASCOPE-RES-131K
    7. 93326
    Prev
    Next
    INDEX
    Explanations

    despite the fact

    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_34/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
     a
    -1.10
     என்று
    -0.98
     both
    -0.87
     an
    -0.86
    trums
    -0.83
    垚
    -0.80
     mathvariant
    -0.79
     Verfasser
    -0.77
     these
    -0.77
    致します
    -0.77
    POSITIVE LOGITS
     fact
    3.25
     faptul
    2.23
     the
    2.09
     Tatsache
    2.08
    fact
    1.86
     اینکه
    1.73
     fakt
    1.53
    Fact
    1.49
     that
    1.48
     FACT
    1.36
    Activations Density 0.062%

    No Known Activations