© 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. 111192
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

    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
    ᅚ
    -1.60
    厹
    -1.55
     gastronomía
    -1.53
     immu
    -1.51
     Enquanto
    -1.46
     hır
    -1.45
     mascarilla
    -1.45
     WHILE
    -1.45
    侂
    -1.42
     Alquiler
    -1.41
    POSITIVE LOGITS
     is
    2.06
     on
    1.79
     for
    1.74
     to
    1.66
     or
    1.65
     has
    1.63
     with
    1.60
     S
    1.60
     in
    1.57
     as
    1.52
    Activations Density 0.197%

    No Known Activations