© 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. 89363
    Prev
    Next
    INDEX
    Explanations

    preposition or conjunction

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

    covering topics

    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
    principal
    0.52
    /
    0.52
    <0xE3>
    0.50
    {
    0.50
    begin
    0.48
    \
    0.46
    princ
    0.45
    P
    0.45
    は
    0.45
    prime
    0.45
    POSITIVE LOGITS
     Konfl
    0.51
     możemy
    0.49
     รวมถึง
    0.49
    कता
    0.49
     เต็ม
    0.47
     konkur
    0.47
     잔
    0.47
     మరింత
    0.46
     देम
    0.46
     കൂടുതൽ
    0.46
    Activations Density 0.000%

    No Known Activations