© 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. 51132
    Prev
    Next
    INDEX
    Explanations

    describing components

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

    lists with numbers and measurements

    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
    也會
    0.59
     accidens
    0.51
     কথাও
    0.51
     niektórych
    0.51
     لكن
    0.50
    Ꭸ
    0.48
     endroits
    0.48
    하기도
    0.46
     fomentar
    0.46
     그리고
    0.46
    POSITIVE LOGITS
     consists
    0.79
     terdiri
    0.69
     gồm
    0.64
     consisted
    0.63
     প্রথমে
    0.62
     consisting
    0.58
     состоит
    0.58
     består
    0.58
     consiste
    0.57
    a
    0.57
    Activations Density 0.075%

    No Known Activations