© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228397
    Prev
    Next
    INDEX
    Explanations

    Jolie ville

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Иванович
    0.47
    兒子
    0.47
    酐
    0.46
     naturels
    0.46
     الاثنين
    0.46
     fruitless
    0.46
     enfe
    0.46
     संस्कृत
    0.44
     exhibiting
    0.44
     земля
    0.44
    POSITIVE LOGITS
    保证
    0.42
    ukk
    0.42
    ggg
    0.41
     penyel
    0.40
    选
    0.39
    ppp
    0.38
    主催
    0.37
    nist
    0.37
    まあ
    0.37
    utti
    0.36
    Activations Density 0.003%

    No Known Activations