© 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. 101851
    Prev
    Next
    INDEX
    Explanations

    are ready to do

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

    creating words, followed by conjunctions

    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
     ذات
    0.48
     مسائل
    0.45
     procedente
    0.43
    َنْ
    0.42
     میرا
    0.42
     خد
    0.41
     সম্পাদক
    0.41
     صفح
    0.41
    LAUNCH
    0.40
     கிரக
    0.40
    POSITIVE LOGITS
    -;
    0.47
     predominantly
    0.45
    ew
    0.44
     togg
    0.44
     predomin
    0.44
    owę
    0.44
    toggle
    0.43
    owej
    0.43
    oz
    0.41
    odge
    0.41
    Activations Density 0.000%

    No Known Activations