© 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. 95544
    Prev
    Next
    INDEX
    Explanations

    cities, islands, and countries

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

    predictable routine

    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
    0.57
    .
    0.56
    archives
    0.46
    strong
    0.45
    2
    0.44
    早い
    0.43
    1
    0.43
    했고
    0.43
    early
    0.43
     billion
    0.42
    POSITIVE LOGITS
     жидкости
    0.57
    材质
    0.54
    橑
    0.52
    橇
    0.51
     погру
    0.51
    窰
    0.51
     транспорти
    0.50
     manipul
    0.49
    祷
    0.48
     женщи
    0.48
    Activations Density 0.001%

    No Known Activations