© 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. 10-GEMMASCOPE-RES-131K
    7. 67528
    Prev
    Next
    INDEX
    Explanations

    either or neither nor

    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
     (
    -1.72
     not
    -1.72
     really
    -1.70
     had
    -1.70
     I
    -1.68
     such
    -1.64
     one
    -1.63
     actually
    -1.59
     because
    -1.59
     without
    -1.59
    POSITIVE LOGITS
    🆗
    1.54
     różnych
    1.53
    NYA
    1.52
    either
    1.48
     Dinas
    1.47
     ส์
    1.47
     différents
    1.45
     installiert
    1.45
     différentes
    1.44
     to
    1.43
    Activations Density 0.060%

    No Known Activations