© 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. 148349
    Prev
    Next
    INDEX
    Explanations

    entering, depict, section, point, extent

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

    meaning of words, phrases, or letters

    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
    的文件
    0.52
     Specify
    0.49
     Majka
    0.47
    }}]
    0.46
    nment
    0.45
    aniyati
    0.44
    的相关
    0.44
    แหน่ง
    0.44
    ielleicht
    0.44
    的神
    0.44
    POSITIVE LOGITS
     корпу
    0.52
    ith
    0.51
     extraordinaire
    0.50
     extrémité
    0.48
     theat
    0.47
     therm
    0.47
     extrémités
    0.47
     х
    0.46
     термо
    0.46
     און
    0.45
    Activations Density 0.001%

    No Known Activations