© 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. 128376
    Prev
    Next
    INDEX
    Explanations

    first and last names

    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
     opinie
    -1.38
     Fotograf
    -1.30
    AllAfrica
    -1.28
     granat
    -1.27
    過ぎて
    -1.25
    Oby
    -1.24
    みましょう
    -1.23
     laine
    -1.23
     zare
    -1.23
     truco
    -1.23
    POSITIVE LOGITS
     this
    1.36
     sprawia
    1.26
    vább
    1.26
     erzä
    1.18
     führte
    1.16
    好像是
    1.14
     andare
    1.14
     it
    1.13
     dziew
    1.13
    omenta
    1.12
    Activations Density 0.013%

    No Known Activations