© 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. 3313
    Prev
    Next
    INDEX
    Explanations

    Widow Ululator

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

    examples or specific items

    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
     균
    0.53
     PES
    0.51
    рани
    0.48
     figli
    0.47
    𝑨
    0.47
     artisti
    0.47
     tub
    0.46
     PSOE
    0.45
     materiali
    0.45
    ❙
    0.45
    POSITIVE LOGITS
    ник
    0.47
     البيانات
    0.46
    伫
    0.46
    atz
    0.45
     ashore
    0.45
     údaje
    0.45
    áš
    0.44
    sky
    0.44
     által
    0.43
    hesive
    0.43
    Activations Density 0.001%

    No Known Activations