© 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. 33718
    Prev
    Next
    INDEX
    Explanations

    determiner followed by noun/clause

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

    conflict, survival, and goals

    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
    Problem
    0.52
    מ
    0.51
    שי
    0.47
    자
    0.47
    ר
    0.46
    ჩ
    0.44
    Caso
    0.43
    ฟ
    0.43
    편집
    0.43
    Questa
    0.43
    POSITIVE LOGITS
    ye
    0.53
     perdón
    0.52
     Chancery
    0.50
     màu
    0.47
    gye
    0.46
     淡
    0.45
    setColor
    0.43
    ిల్
    0.43
     trägt
    0.43
     dẫn
    0.43
    Activations Density 0.000%

    No Known Activations