© 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. 8646
    Prev
    Next
    INDEX
    Explanations

    calculate, enable, criticism, every

    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
     (
    0.50
     breakfast
    0.48
     Pinterest
    0.44
     Young
    0.44
     iii
    0.44
    0.43
     github
    0.43
     young
    0.43
     ("
    0.43
     ii
    0.43
    POSITIVE LOGITS
    rodní
    0.54
    訨
    0.53
     километ
    0.52
     методи
    0.52
    }^{*}=\
    0.50
    트롤
    0.48
    二百
    0.47
     ಯಾವುದ
    0.47
     certificados
    0.47
    cí
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.