© 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. 21705
    Prev
    Next
    INDEX
    Explanations

    writing

    np_acts-logits-general · gemini-2.5-flash-lite

    requests to write

    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
    یک
    0.70
    سازی
    0.70
    tól
    0.67
    к
    0.67
    liği
    0.66
    大きさ
    0.65
     señales
    0.65
    dı
    0.64
    𝗸
    0.63
     boyut
    0.62
    POSITIVE LOGITS
    寫
    0.98
     write
    0.95
    Write
    0.95
     Write
    0.94
     scris
    0.88
     เขียน
    0.86
     escrever
    0.85
     написать
    0.84
     menulis
    0.82
     escrib
    0.81
    Activations Density 0.088%

    No Known Activations