© 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. 73534
    Prev
    Next
    INDEX
    Explanations

    acknowledged by Mason

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

    power dynamics and consequences

    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
    英文
    0.52
     buddhav
    0.46
     Уен
    0.45
     projek
    0.44
    通讯
    0.44
    韵
    0.43
     testifies
    0.43
    াঙ্গীর
    0.43
    OpportunitiesBy
    0.43
     attraverso
    0.42
    POSITIVE LOGITS
     Citrus
    0.54
     Zeta
    0.54
     Sony
    0.52
     Rial
    0.51
     Curb
    0.49
     Zion
    0.48
     Fukushima
    0.46
    Sony
    0.45
    \
    0.45
     Siberia
    0.45
    Activations Density 0.000%

    No Known Activations