© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 54111
    Prev
    Next
    INDEX
    Explanations

    wooden coder's notebook journal

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

    expanding into new sectors

    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
     
    0.54
     lawyer
    0.48
     lawyers
    0.47
     Lawyer
    0.43
     United
    0.42
     Foreign
    0.42
     portavoz
    0.42
     잠깐
    0.42
    ↵
    0.42
     Israeli
    0.41
    POSITIVE LOGITS
     pédicule
    0.54
    Sqrt
    0.54
     дослі
    0.52
     ferrugineux
    0.49
     approu
    0.48
     lymphatiques
    0.47
     pedibusque
    0.47
     eignet
    0.47
    ḫ
    0.46
    ɸ
    0.46
    Activations Density 0.001%

    No Known Activations