© 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. 161090
    Prev
    Next
    INDEX
    Explanations

    Matric, thriller, descriptive words, technology

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

    beginners Squad space console long period

    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
     drugih
    0.58
     actief
    0.50
     anderen
    0.50
    收聽
    0.48
    ing
    0.48
     alamu
    0.47
    "));
    0.46
    聲音
    0.46
     jungen
    0.46
     其他
    0.45
    POSITIVE LOGITS
     Matric
    0.51
     thriller
    0.46
    供应链
    0.45
     Descripción
    0.44
     devastated
    0.43
    テクノ
    0.43
     converted
    0.43
     Converter
    0.42
    漼
    0.42
    াদী
    0.42
    Activations Density 0.000%

    No Known Activations