© 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. 10-GEMMASCOPE-RES-131K
    7. 14715
    Prev
    Next
    INDEX
    Explanations

    study, office, nursery, library, room

    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
    pastebin
    -1.63
    蓠
    -1.59
     baterie
    -1.57
    jedno
    -1.53
     Израи
    -1.52
     keď
    -1.52
     interesan
    -1.50
    lawesi
    -1.49
     kinderen
    -1.48
    vignon
    -1.48
    POSITIVE LOGITS
     other
    1.77
     of
    1.59
    y
    1.55
    in
    1.54
    p
    1.51
    d
    1.47
    this
    1.47
    h
    1.46
     more
    1.44
     /
    1.43
    Activations Density 0.014%

    No Known Activations