© 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. 102783
    Prev
    Next
    INDEX
    Explanations

    Ranger and Francis names

    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
     così
    -2.50
    是
    -2.44
    -2.42
    1
    -2.30
    也没
    -2.28
    皛
    -2.23
    {
    -2.17
    瑨
    -2.14
     aktualisiert
    -2.09
    真的是
    -2.06
    POSITIVE LOGITS
     осторо
    2.38
    because
    2.28
     entice
    2.23
    🍺
    2.22
    OUTUBE
    2.22
    😵
    2.22
     offiziellen
    2.20
     täglichen
    2.13
     Also
    2.11
     speziellen
    2.11
    Activations Density 0.001%

    No Known Activations