© 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. 155205
    Prev
    Next
    INDEX
    Explanations

    language identification or multilingual context

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

    familiar with, a feel for, avoid

    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
    0.59
    0.50
     I
    0.50
     `
    0.48
    aini
    0.47
    g
    0.46
    ocon
    0.46
     L
    0.45
    uc
    0.45
     crystall
    0.45
    POSITIVE LOGITS
    ਕ
    0.55
    我可以
    0.54
     Ausdruck
    0.51
     mogelijk
    0.50
     Untersuch
    0.49
    betriebnahme
    0.49
    而且
    0.47
    ٦
    0.47
    𝖐
    0.47
    瞽
    0.47
    Activations Density 0.001%

    No Known Activations