© 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. 132178
    Prev
    Next
    INDEX
    Explanations

    steel refers, lost wax

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

    value / lift / life

    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
     několika
    0.48
     తెలి
    0.47
     cơm
    0.47
     Nhưng
    0.46
     kering
    0.46
     ausreichend
    0.44
     Prakt
    0.44
    杩
    0.43
     Have
    0.43
     bốn
    0.43
    POSITIVE LOGITS
    aircraft
    0.52
    فاوت
    0.48
    थ
    0.48
    Е
    0.47
    %.
    0.47
    рым
    0.46
    VALUE
    0.45
    ITEMS
    0.45
    يران
    0.45
    nomenclature
    0.44
    Activations Density 0.003%

    No Known Activations