© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104442
    Prev
    Next
    INDEX
    Explanations

    commercial license or copy

    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
     bascul
    -1.38
     peines
    -1.35
     verko
    -1.34
     onPostExecute
    -1.34
     fraî
    -1.32
    鸰
    -1.28
    voer
    -1.27
    𖧵
    -1.27
     superbe
    -1.24
    hitung
    -1.24
    POSITIVE LOGITS
     license
    1.52
     on
    1.43
     through
    1.30
    pects
    1.18
     permits
    1.16
     when
    1.12
     permit
    1.11
     Veränderung
    1.09
     they
    1.09
     Permit
    1.08
    Activations Density 0.092%

    No Known Activations