© 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. 233805
    Prev
    Next
    INDEX
    Explanations

    taxes and storage

    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
     toggle
    0.45
     voh
    0.45
    u
    0.43
     tov
    0.42
    BinaryOperation
    0.42
     tö
    0.41
     softwares
    0.41
     simplic
    0.40
     contents
    0.40
     togg
    0.40
    POSITIVE LOGITS
     দম
    0.54
     зона
    0.51
    ˍ
    0.50
    angé
    0.47
    ۹
    0.47
    $:
    0.46
    মারের
    0.46
    Á
    0.46
     দেখার
    0.45
     CLIENTI
    0.45
    Activations Density 0.001%

    No Known Activations