© 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. 38906
    Prev
    Next
    INDEX
    Explanations

    hidden input tags

    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
     zwanzig
    -1.66
    atmosphère
    -1.51
     tzw
    -1.51
    dymyr
    -1.44
    矬
    -1.41
     gekauft
    -1.40
    those
    -1.38
     hundert
    -1.36
    should
    -1.35
    )
    -1.33
    POSITIVE LOGITS
     for
    2.47
     one
    1.50
     Both
    1.46
     With
    1.42
     Quite
    1.41
     Página
    1.41
    世间
    1.39
    的目的
    1.38
     There
    1.36
     However
    1.34
    Activations Density 0.003%

    No Known Activations