© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123834
    Prev
    Next
    INDEX
    Explanations

    A: lists

    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
    \
    -1.81
    ೢ
    -1.66
    ka
    -1.58
     dwie
    -1.56
     #
    -1.55
     dieser
    -1.55
    pegno
    -1.53
     our
    -1.52
     http
    -1.52
    她就
    -1.48
    POSITIVE LOGITS
    }$_
    1.55
     histoires
    1.55
     montagnes
    1.55
     journalistes
    1.55
     dizaines
    1.53
    褔
    1.52
    "$_
    1.52
     trio
    1.52
     Fácil
    1.50
    bied
    1.48
    Activations Density 0.000%

    No Known Activations