© 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. 67780
    Prev
    Next
    INDEX
    Explanations

    iTunes Apple subscribe

    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
     blauw
    -1.40
     automó
    -1.34
     hver
    -1.32
     arrêter
    -1.32
     occuper
    -1.30
     privacidad
    -1.30
     lèvres
    -1.30
     ibid
    -1.30
    搋
    -1.28
     Arkivert
    -1.27
    POSITIVE LOGITS
     by
    1.73
     four
    1.38
     just
    1.33
     all
    1.32
     not
    1.32
     of
    1.32
     some
    1.30
     first
    1.30
     eight
    1.28
     six
    1.27
    Activations Density 0.059%

    No Known Activations