© 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. 65994
    Prev
    Next
    INDEX
    Explanations

    increasing, expensive, orders

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

    conveying tone and emotion

    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
    ہی
    0.54
    㕕
    0.49
    血液
    0.48
    矛盾
    0.46
    роки
    0.46
    時代
    0.44
    给予
    0.43
     человека
    0.43
    稚
    0.43
     miliar
    0.43
    POSITIVE LOGITS
    lette
    0.48
     (--
    0.46
    rangea
    0.46
    fragt
    0.45
    tun
    0.45
     شوید
    0.45
     laureate
    0.45
    preset
    0.44
    awać
    0.44
    gart
    0.44
    Activations Density 0.000%

    No Known Activations