© 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. 30591
    Prev
    Next
    INDEX
    Explanations

    girl followed by context

    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
    thansa
    -1.20
     male
    -1.17
     hommes
    -1.14
    哔
    -1.06
    Mascul
    -1.06
     людей
    -1.05
    是这样的
    -1.05
     férfi
    -1.05
     insanların
    -1.05
    Cooler
    -1.05
    POSITIVE LOGITS
    👧
    1.56
     who
    1.55
    girl
    1.20
    hood
    1.20
    шки
    1.11
    ,(
    1.11
     Girl
    1.08
     Scout
    1.07
    out
    1.05
     嘉
    1.05
    Activations Density 0.011%

    No Known Activations