© 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. 11908
    Prev
    Next
    INDEX
    Explanations

    prediction and updating methods

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

    learning, control, and estimation

    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
    招标
    0.61
    商标
    0.61
    税务
    0.59
    Toolbar
    0.59
    现代化
    0.59
    高志森
    0.59
    槟
    0.59
    名稱
    0.58
    ꔰ
    0.58
     शिल्पा
    0.57
    POSITIVE LOGITS
     vectors
    0.84
     stochastic
    0.80
     prediction
    0.79
     update
    0.77
     predict
    0.76
     velocity
    0.73
     calculate
    0.73
     weighted
    0.73
     Kalman
    0.73
     learning
    0.72
    Activations Density 0.004%

    No Known Activations