© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 15761
    Prev
    Next
    INDEX
    Explanations

    serving USA

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

    catch up soon though

    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
     tellus
    0.48
     selatan
    0.48
     endothelial
    0.47
     molecular
    0.45
     Yellowstone
    0.45
    ה
    0.44
     declarar
    0.44
     proclam
    0.44
     flor
    0.44
     lavado
    0.44
    POSITIVE LOGITS
    OD
    0.55
    Xd
    0.54
    that
    0.49
    obie
    0.48
     تبدیلی
    0.48
    0
    0.47
    Capability
    0.47
    ный
    0.46
    чний
    0.46
    żenie
    0.46
    Activations Density 0.000%

    No Known Activations