© 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. 34-GEMMASCOPE-RES-131K
    7. 117332
    Prev
    Next
    INDEX
    Explanations

    Rolex watches and features

    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_34/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
    quía
    -0.83
     Commissioners
    -0.82
     Limestone
    -0.77
     Acuerdo
    -0.77
     União
    -0.77
    vak
    -0.76
     印
    -0.75
    pado
    -0.75
    rubin
    -0.75
    童
    -0.74
    POSITIVE LOGITS
     Rolex
    1.41
    ROL
    1.03
    Role
    0.98
     Oyster
    0.93
     Role
    0.85
     کاملا
    0.84
     Roles
    0.83
    Roles
    0.82
     oyster
    0.80
    inous
    0.76
    Activations Density 0.009%

    No Known Activations