© 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. 160678
    Prev
    Next
    INDEX
    Explanations

    operates

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

    happening, frustration, may

    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
    eba
    0.52
    ối
    0.50
     exposición
    0.46
    bei
    0.45
    ój
    0.45
    exposition
    0.44
    ཅ
    0.44
    ඉ
    0.44
    ้ง
    0.43
     বিকা
    0.43
    POSITIVE LOGITS
     Champlain
    0.55
     Susan
    0.49
    Susan
    0.49
     Rhet
    0.48
     Sugar
    0.48
     Rodney
    0.48
     Clifford
    0.47
    Sugar
    0.47
    sG
    0.47
    sugar
    0.47
    Activations Density 0.000%

    No Known Activations