© 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. 100461
    Prev
    Next
    INDEX
    Explanations

    style description

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

    programming questions or syntax

    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
    ดา
    0.54
    فعيل
    0.53
    ט
    0.52
    ла
    0.48
    ত
    0.48
    สี
    0.47
    ท
    0.47
    יו
    0.46
    จ
    0.45
    ทาน
    0.45
    POSITIVE LOGITS
     Estat
    0.54
     sovi
    0.52
     equil
    0.51
     یہودی
    0.51
     یہودیوں
    0.50
     Doctorate
    0.50
     installs
    0.50
     instal
    0.50
     nirv
    0.50
    attiyam
    0.49
    Activations Density 0.000%

    No Known Activations