© 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. 16-GEMMASCOPE-2-RES-16K
    7. 499
    Prev
    Next
    INDEX
    Explanations

    and pronoun

    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_16_width_16k_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
     Bogotá
    0.49
    r
    0.49
     Lieut
    0.49
     IntPtr
    0.47
     Bicycle
    0.46
     Đầu
    0.45
    ျ
    0.45
    ía
    0.44
     الأمير
    0.44
     Ultra
    0.43
    POSITIVE LOGITS
    werte
    0.59
    ンダー
    0.58
    İZ
    0.57
    ﾓ
    0.54
    PA
    0.53
    वर्क
    0.53
    ძლიათ
    0.52
     dersimizde
    0.51
     biasing
    0.51
    .",
    0.50
    Activations Density 0.000%

    No Known Activations