© 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. 135427
    Prev
    Next
    INDEX
    Explanations

    rights, regulations, or legal notices

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

    years, occurs, reactions

    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
    Га
    0.50
     meget
    0.49
    \
    0.46
     conseguiu
    0.43
     sampel
    0.43
    ʊ
    0.43
     muito
    0.43
     оригі
    0.41
     retreated
    0.41
     mẫu
    0.41
    POSITIVE LOGITS
    纤维
    0.54
    িল্প
    0.53
    regierung
    0.50
    businesses
    0.50
    Municipal
    0.48
    یات
    0.46
     pano
    0.46
    из
    0.45
    출
    0.45
     appending
    0.45
    Activations Density 0.001%

    No Known Activations