© 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. 22-GEMMASCOPE-RES-131K
    7. 25678
    Prev
    Next
    INDEX
    Explanations

    professions and roles

    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_22/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
     Many
    -1.03
     many
    -0.97
     Before
    -0.95
    Semitism
    -0.95
     invigor
    -0.92
     Despite
    -0.91
     Both
    -0.87
     less
    -0.87
     had
    -0.86
     attempting
    -0.86
    POSITIVE LOGITS
    ᚑ
    1.11
     bloquer
    1.09
     ingenieros
    1.08
    tawesome
    1.07
     heo
    1.05
     ส์
    1.05
    }(),
    1.04
    bảng
    1.04
     Ă
    1.04
    anyahu
    1.03
    Activations Density 0.037%

    No Known Activations