© 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. 33660
    Prev
    Next
    INDEX
    Explanations

    executive positions

    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
     -
    -1.27
     либо
    -1.27
    を選択します
    -1.22
    >
    -1.21
    を行いました
    -1.20
    を行います
    -1.20
     it
    -1.19
    J
    -1.18
    N
    -1.18
    _
    -1.17
    POSITIVE LOGITS
     of
    3.06
     at
    1.52
     benzin
    1.49
     in
    1.37
     ideen
    1.36
     hunde
    1.34
     gangen
    1.32
     bär
    1.27
     himmel
    1.27
     của
    1.26
    Activations Density 0.014%

    No Known Activations