© 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. 55060
    Prev
    Next
    INDEX
    Explanations

    easy rolling, act and, broad shoulders, green dot

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

    start of response or transition

    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
    শোধ
    0.56
    ᱢ
    0.47
     decay
    0.46
     demás
    0.46
     हेल्प
    0.45
    જનો
    0.45
    ાસ
    0.44
     एनी
    0.42
    ｪ
    0.42
     হট
    0.42
    POSITIVE LOGITS
    คุณ
    0.46
    <caption>
    0.45
     you
    0.44
     человеку
    0.43
     Вам
    0.43
     нашим
    0.43
     centrally
    0.42
    ó
    0.42
     людям
    0.42
    IRIS
    0.42
    Activations Density 0.000%

    No Known Activations