© 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. 58071
    Prev
    Next
    INDEX
    Explanations

    C# unit test and web api attributes

    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
     from
    -0.90
     као
    -0.85
    𝓬
    -0.82
    ۤ
    -0.80
     (
    -0.79
     for
    -0.79
    )}$,
    -0.79
     }}</
    -0.79
    :
    -0.77
     some
    -0.77
    POSITIVE LOGITS
     geladen
    0.94
     gelassen
    0.91
     reichlich
    0.89
     företag
    0.85
    nologie
    0.84
    nalités
    0.83
    equila
    0.82
    czaj
    0.82
     pantallas
    0.82
     archite
    0.81
    Activations Density 0.004%

    No Known Activations