© 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. 138121
    Prev
    Next
    INDEX
    Explanations

    Montreal, polar bears, discipline

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

    This conversation revolves around

    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
    蘇
    0.47
    বর্তমান
    0.46
     Nederland
    0.45
    杰
    0.45
    编码
    0.45
     wahrscheinlich
    0.45
    ubehör
    0.45
     Tested
    0.44
    了大
    0.44
    㢦
    0.44
    POSITIVE LOGITS
     دم
    0.50
    :
    0.48
     hư
    0.43
     ¼
    0.43
    finish
    0.43
     :=
    0.42
     beams
    0.41
    owe
    0.41
     mercy
    0.41
     to
    0.41
    Activations Density 0.001%

    No Known Activations