© 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. 89874
    Prev
    Next
    INDEX
    Explanations

    common phrases and combinations

    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
    벗
    0.55
    នៃ
    0.52
    蓍
    0.51
     അറ
    0.50
    皑
    0.48
    MEDICAL
    0.47
    ഹു
    0.47
    𐰆
    0.47
    姍
    0.46
     Bibli
    0.46
    POSITIVE LOGITS
     displays
    0.50
    ig
    0.49
    eda
    0.49
    enches
    0.48
     receives
    0.47
    any
    0.46
     carries
    0.45
     allocates
    0.45
    ignore
    0.44
     ignores
    0.44
    Activations Density 0.001%

    No Known Activations