© 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. 8482
    Prev
    Next
    INDEX
    Explanations

    named entities and specific phrases

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

    OSI, daily, meritocracy, stifle, flows

    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
    everyone
    0.54
     zonal
    0.53
     stored
    0.50
     everyone
    0.50
    mk
    0.49
    t
    0.49
    stored
    0.48
    arul
    0.48
     taxonomic
    0.48
     Yeon
    0.47
    POSITIVE LOGITS
     عن
    0.56
     смысла
    0.52
    ។
    0.52
     tentang
    0.51
    ።
    0.50
    ឬ
    0.50
    嶷
    0.50
     выступления
    0.49
    ة
    0.49
    行动
    0.49
    Activations Density 0.000%

    No Known Activations