© 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. 52783
    Prev
    Next
    INDEX
    Explanations

    uncertainties and points

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

    skepticism, doubts, or refusals

    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
    更新
    0.54
    lanır
    0.54
    下载
    0.52
    GENERAL
    0.51
    Decoder
    0.50
    值为
    0.49
    纓
    0.49
    ২
    0.48
    function
    0.48
    Number
    0.48
    POSITIVE LOGITS
     dimers
    0.57
     barista
    0.54
     opinions
    0.51
     skepticism
    0.51
     partur
    0.51
     curd
    0.50
     suspicions
    0.49
     kaj
    0.48
     tros
    0.48
     uncertainties
    0.48
    Activations Density 0.000%

    No Known Activations