© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78129
    Prev
    Next
    INDEX
    Explanations

    based on

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

    aligns with objectives

    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
    ўцаў
    0.48
     overse
    0.45
    .;
    0.43
     caretaker
    0.42
    łow
    0.42
    ̀i
    0.41
    essori
    0.40
    udrait
    0.40
     college
    0.40
     caregiver
    0.40
    POSITIVE LOGITS
    সুন্দর
    0.50
     диагностики
    0.47
    酊
    0.46
    专题
    0.45
    探测
    0.45
    逗
    0.45
    地图
    0.44
    成果
    0.44
    মালা
    0.44
     Aufgaben
    0.43
    Activations Density 0.004%

    No Known Activations