© 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. 22-GEMMASCOPE-RES-131K
    7. 26567
    Prev
    Next
    INDEX
    Explanations

    initiating requests or explanations

    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_22/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
    Months
    -1.27
     erfolgreich
    -1.09
    formatics
    -1.05
    ludes
    -1.03
    ایان
    -1.03
    ᾶ
    -1.00
    انجليز
    -0.98
     صلى
    -0.97
     herbes
    -0.97
     Méri
    -0.96
    POSITIVE LOGITS
     about
    1.52
     then
    1.48
     before
    1.41
     again
    1.37
     briefly
    1.33
     quickly
    1.31
     immediately
    1.23
     that
    1.23
     back
    1.21
     two
    1.16
    Activations Density 0.004%

    No Known Activations