© 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. 34-GEMMASCOPE-RES-131K
    7. 117435
    Prev
    Next
    INDEX
    Explanations

    FIG

    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_34/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
     how
    -1.38
     so
    -1.34
    -1.23
    setcounter
    -1.22
     fungerer
    -1.18
     would
    -1.16
     as
    -1.16
     before
    -1.13
     prieš
    -1.09
     ganske
    -1.07
    POSITIVE LOGITS
     Fourteen
    1.57
     Sixteen
    1.55
     Fifteen
    1.54
     Eighteen
    1.45
     quinze
    1.42
     seventeen
    1.39
     Nineteen
    1.38
     Thirteen
    1.34
     sixteen
    1.29
     Seventeen
    1.27
    Activations Density 0.100%

    No Known Activations