© 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. 74675
    Prev
    Next
    INDEX
    Explanations

    residency, bra, watershed, checking, reject

    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
     there
    -2.34
     have
    -1.80
     into
    -1.72
     they
    -1.67
     no
    -1.55
     some
    -1.55
     is
    -1.52
     are
    -1.45
    ,
    -1.41
     all
    -1.40
    POSITIVE LOGITS
     båda
    1.80
     medži
    1.71
     liknande
    1.61
    Pá
    1.59
     vux
    1.59
     varandra
    1.55
     ángeles
    1.53
     jūsų
    1.52
     dessutom
    1.50
     taal
    1.47
    Activations Density 0.207%

    No Known Activations