© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34459
    Prev
    Next
    INDEX
    Explanations

    documentation links

    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
     and
    -1.55
    を行いました
    -1.30
     this
    -1.19
     negociar
    -1.13
     kontaktu
    -1.13
     zahlreichen
    -1.04
    krä
    -1.02
    鋮
    -1.00
    Quercus
    -1.00
     establecidos
    -0.99
    POSITIVE LOGITS
     hins
    1.07
     messen
    1.06
     krank
    0.99
    总之
    0.99
     moderno
    0.99
    ↵↵
    0.98
     gese
    0.96
     Describes
    0.94
     proposito
    0.94
    нную
    0.94
    Activations Density 0.023%

    No Known Activations