© 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. 129057
    Prev
    Next
    INDEX
    Explanations

    general, occasionally, to, idea, aimed, early, apparently

    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
     in
    -2.44
     it
    -2.42
     its
    -1.85
     three
    -1.83
     any
    -1.81
     over
    -1.80
     has
    -1.80
     four
    -1.77
     should
    -1.75
     five
    -1.70
    POSITIVE LOGITS
     variétés
    1.63
     geheim
    1.62
     disques
    1.56
     gericht
    1.52
    werkers
    1.51
     gespe
    1.50
     puissent
    1.49
     verhind
    1.49
     centaines
    1.48
     demandes
    1.48
    Activations Density 0.347%

    No Known Activations