© 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. 22-GEMMASCOPE-RES-131K
    7. 129752
    Prev
    Next
    INDEX
    Explanations

    professions or 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
    裡的
    -1.10
     felhasznál
    -1.08
     móds
    -1.02
    视为
    -0.92
    usammen
    -0.91
    افة
    -0.88
    岁的
    -0.88
     by
    -0.88
    彼らの
    -0.88
    的东西
    -0.88
    POSITIVE LOGITS
     who
    2.39
     whom
    1.70
     ktorí
    1.23
    who
    1.23
     hired
    1.15
     nodig
    1.11
    에게
    1.09
     kteří
    1.09
    гән
    1.07
    whom
    1.05
    Activations Density 0.058%

    No Known Activations