© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20044
    Prev
    Next
    INDEX
    Explanations

    Noob questions or specific words

    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
     différents
    -1.63
    丅
    -1.59
     perfons
    -1.52
     verschillende
    -1.48
     plusieurs
    -1.48
    different
    -1.44
    pson
    -1.38
     différentes
    -1.34
     abbildung
    -1.33
    毳
    -1.33
    POSITIVE LOGITS
     only
    2.52
     any
    1.82
     Only
    1.58
     ONLY
    1.54
     or
    1.48
     in
    1.48
     like
    1.48
     What
    1.48
    Only
    1.44
     Perhaps
    1.44
    Activations Density 0.113%

    No Known Activations