© 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. 180892
    Prev
    Next
    INDEX
    Explanations

    payment charge

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

    for modern attendance medicine

    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
     vacaciones
    0.44
     proportion
    0.43
     absence
    0.42
     voulez
    0.41
     garantire
    0.41
     touch
    0.41
     presupuesto
    0.41
    n
    0.41
     sequel
    0.40
     yell
    0.40
    POSITIVE LOGITS
    鳍
    0.57
    唇
    0.53
    เมตร
    0.52
     बैंक
    0.50
    整形
    0.48
    жения
    0.47
    বক
    0.47
    盽
    0.46
     উন্নয়নে
    0.46
    鰭
    0.46
    Activations Density 0.001%

    No Known Activations