© 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. 66924
    Prev
    Next
    INDEX
    Explanations

    Setting context with "With"

    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
     has
    -2.20
     by
    -2.19
     when
    -2.13
     for
    -2.11
     because
    -2.09
     requires
    -2.06
    in
    -2.06
     two
    -2.03
     does
    -2.03
     should
    -2.02
    POSITIVE LOGITS
    蓠
    2.52
    泐
    2.50
    𓐍
    2.22
     suffisamment
    2.20
    鹩
    2.05
    瞜
    1.98
    跸
    1.98
    媪
    1.98
    vetrain
    1.92
    ⠀⠀⠀⠀⠀⠀⠀⠀
    1.92
    Activations Density 0.036%

    No Known Activations