© 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. 181934
    Prev
    Next
    INDEX
    Explanations

    expressing needs and quantity

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

    exceptions and obstacles

    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
    ).
    0.52
    eigen
    0.50
    ].
    0.49
    t
    0.48
    m
    0.48
    /
    0.48
    ↵↵
    0.46
    漢
    0.46
    y
    0.46
    法の
    0.45
    POSITIVE LOGITS
     还
    0.55
     nejsou
    0.53
     স্ট্যান্ড
    0.52
     blijft
    0.52
     输出
    0.50
     dís
    0.49
     ještě
    0.49
    خرج
    0.48
    ണ്ണം
    0.48
     Chưa
    0.48
    Activations Density 0.004%

    No Known Activations