© 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. 236509
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions and diverse terms

    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
    ẩu
    0.56
    诋
    0.55
    hera
    0.49
    ティー
    0.48
    mesi
    0.47
    gua
    0.47
    riy
    0.47
    ru
    0.46
     mga
    0.46
     perangkat
    0.46
    POSITIVE LOGITS
    脹
    0.43
    coon
    0.41
     காரங்கள்
    0.40
     Spitz
    0.40
     الأحمر
    0.40
    يكون
    0.40
     terroir
    0.39
     Blond
    0.38
     Bluff
    0.38
     पोषण
    0.38
    Activations Density 0.001%

    No Known Activations