© 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. 67731
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers

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

    foreign language words

    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
    r
    0.55
    tr
    0.55
    trn
    0.54
    р
    0.52
    u
    0.52
    ay
    0.51
    !',
    0.51
    pt
    0.50
    create
    0.50
    $^{
    0.50
    POSITIVE LOGITS
     Aunt
    0.45
     جماعت
    0.44
    Penumpang
    0.44
     gái
    0.43
     movieList
    0.43
     antecedent
    0.43
     Lagoon
    0.42
     collusion
    0.42
     kidd
    0.42
     atteggi
    0.42
    Activations Density 0.001%

    No Known Activations