© 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. 210907
    Prev
    Next
    INDEX
    Explanations

    breathable material, electronic transfer, setting instructions

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

    witnessed empires rise

    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
     ਜਾਂ
    0.47
    專業
    0.46
    ச்சியை
    0.46
     শতকরা
    0.46
     Connelly
    0.45
     Kendrick
    0.45
    莗
    0.44
     %[
    0.44
     венти
    0.44
     дверь
    0.44
    POSITIVE LOGITS
    open
    0.48
     ramai
    0.45
    Ephemeral
    0.44
    p
    0.43
     ganado
    0.43
    da
    0.42
    imation
    0.42
     dihar
    0.42
    chooser
    0.42
     motionProxy
    0.41
    Activations Density 0.001%

    No Known Activations