© 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. 84057
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    d
    -2.03
     was
    -1.80
     -
    -1.77
    f
    -1.74
    g
    -1.68
    b
    -1.67
     of
    -1.60
     There
    -1.51
     Another
    -1.51
    a
    -1.50
    POSITIVE LOGITS
     those
    1.98
     vodu
    1.75
     kontaktu
    1.72
     textu
    1.67
    larla
    1.63
     habile
    1.61
     чрезвы
    1.58
    焄
    1.58
     recub
    1.55
    之为
    1.55
    Activations Density 0.004%

    No Known Activations