© 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. 14569
    Prev
    Next
    INDEX
    Explanations

    describes states, actions, or concepts

    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
     fout
    -1.33
    may
    -1.26
     vold
    -1.23
    ll
    -1.23
     keny
    -1.20
     inox
    -1.16
     hok
    -1.14
     EXERCISES
    -1.14
     BATTERY
    -1.13
     tull
    -1.13
    POSITIVE LOGITS
     Erfüllung
    1.52
    Those
    1.50
    Sometimes
    1.42
     Absicht
    1.42
     Ergänzung
    1.41
     Vorbereitung
    1.38
     Notwendigkeit
    1.36
     those
    1.34
    gafas
    1.34
     Durchführung
    1.33
    Activations Density 0.334%

    No Known Activations