© 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. 40988
    Prev
    Next
    INDEX
    Explanations

    published texts or posts

    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
    losure
    -1.44
    aphne
    -1.43
    katapos
    -1.41
    ,
    -1.41
    髕
    -1.38
    ijnlijk
    -1.38
    pochette
    -1.38
     Witkin
    -1.34
     Vrbo
    -1.34
     あります
    -1.34
    POSITIVE LOGITS
     is
    1.71
    not
    1.41
    OPHER
    1.32
    .
    1.31
    にします
    1.30
     the
    1.30
     
    1.28
    ana
    1.27
    no
    1.26
    とはいえ
    1.26
    Activations Density 0.009%

    No Known Activations