© 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. 39610
    Prev
    Next
    INDEX
    Explanations

    also introducing further information

    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
    itettura
    -1.47
    aching
    -1.37
    雖然
    -1.28
    AFTER
    -1.27
    Wednesday
    -1.27
     Ito
    -1.27
    NotBlank
    -1.25
     ρ
    -1.22
     acheter
    -1.21
    ˃
    -1.20
    POSITIVE LOGITS
     then
    2.17
     this
    1.88
     our
    1.80
     because
    1.80
     which
    1.66
     makes
    1.65
     if
    1.57
     creates
    1.56
     when
    1.56
     my
    1.52
    Activations Density 0.035%

    No Known Activations