© 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. 101946
    Prev
    Next
    INDEX
    Explanations

    business days

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

    parts, tragedy, just

    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
     cij
    0.48
     التالي
    0.48
     siguiente
    0.47
     regionale
    0.46
     messenger
    0.46
     deepen
    0.45
    、
    0.45
     hik
    0.45
    т
    0.45
     Dr
    0.44
    POSITIVE LOGITS
    㙋
    0.50
    㠱
    0.50
    ungkin
    0.47
    稈
    0.47
    urangi
    0.46
    ಹಾರ
    0.46
    nington
    0.46
    imageBase
    0.45
    ionized
    0.45
    icznej
    0.45
    Activations Density 0.000%

    No Known Activations