© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 233101
    Prev
    Next
    INDEX
    Explanations

    bonus, free, slot

    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
    ாண்டு
    0.44
     bowl
    0.42
     되고
    0.40
     kojem
    0.39
     magazine
    0.38
     repetitive
    0.38
    ходим
    0.38
    )
    0.38
    ologies
    0.38
    区的
    0.38
    POSITIVE LOGITS
     მთ
    0.50
    mère
    0.48
    бот
    0.48
     navegador
    0.48
     Olha
    0.48
    setlength
    0.48
     Herv
    0.47
    hiver
    0.47
     दिवाली
    0.46
    ઞ
    0.46
    Activations Density 0.000%

    No Known Activations