© 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. 65107
    Prev
    Next
    INDEX
    Explanations

    presence and location

    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
    ようです
    -1.44
     erity
    -1.35
     mediante
    -1.34
     ermöglicht
    -1.32
     melalui
    -1.29
     mitään
    -1.27
     mitä
    -1.26
     attraverso
    -1.25
     kaikk
    -1.25
     berichtet
    -1.23
    POSITIVE LOGITS
     there
    3.20
     in
    3.00
     on
    2.30
     هناك
    1.81
     at
    1.78
     here
    1.68
    there
    1.57
     out
    1.56
     THERE
    1.45
    THERE
    1.43
    Activations Density 0.045%

    No Known Activations