© 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. 105277
    Prev
    Next
    INDEX
    Explanations

    comparison, state, or condition

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

    accuracy, GDP, or writing values

    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
    him
    0.55
    পুরুষ
    0.54
    uccio
    0.49
    ӓ
    0.48
    conoc
    0.48
    erek
    0.48
    isn
    0.48
    homme
    0.47
    cyj
    0.46
     пожа
    0.46
    POSITIVE LOGITS
     tray
    0.46
     trays
    0.45
    监听
    0.45
    对比
    0.45
     seam
    0.43
     moch
    0.43
     slush
    0.43
    滞
    0.43
     slat
    0.42
     Birmingham
    0.42
    Activations Density 0.000%

    No Known Activations