© 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. 227614
    Prev
    Next
    INDEX
    Explanations

    career, warranty, next posts

    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
    가
    0.51
    两大
    0.49
    라인
    0.49
    ता
    0.47
    leaving
    0.47
    娌
    0.47
    ligne
    0.46
    ची
    0.46
    倝
    0.46
    ทีม
    0.46
    POSITIVE LOGITS
    0.51
     Painter
    0.46
     Lomond
    0.46
     Livermore
    0.46
     Loma
    0.46
     Connell
    0.45
     Leicester
    0.45
     Vista
    0.44
     Depos
    0.44
    ,!
    0.44
    Activations Density 0.000%

    No Known Activations