© 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. 42116
    Prev
    Next
    INDEX
    Explanations

    livejasmin

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

    legal arguments about discrimination

    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
    ALO
    0.46
     malad
    0.44
     비슷
    0.42
     brain
    0.41
     hamp
    0.40
     dictionary
    0.39
     diplomatic
    0.39
    綰
    0.39
    ทรั
    0.38
     duality
    0.38
    POSITIVE LOGITS
     Markup
    0.48
     உள்ளட
    0.46
     மெ
    0.45
     அதிக
    0.44
    标注
    0.44
     interspersed
    0.44
    JavaScript
    0.43
    étend
    0.43
    景区
    0.42
     MSNBC
    0.42
    Activations Density 0.000%

    No Known Activations