© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8790
    Prev
    Next
    INDEX
    Explanations

    const keyword before types

    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
     การ
    -1.76
     wondrous
    -1.66
     Cette
    -1.59
    ⎔
    -1.59
     vijf
    -1.58
     PERFECT
    -1.57
     sommes
    -1.55
     vermel
    -1.51
     revered
    -1.50
     ludicrous
    -1.49
    POSITIVE LOGITS
     of
    2.33
     where
    1.95
     for
    1.88
     beserta
    1.80
     also
    1.80
     when
    1.68
     additional
    1.66
     will
    1.65
     similar
    1.65
     espres
    1.64
    Activations Density 0.004%

    No Known Activations