© 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. 156992
    Prev
    Next
    INDEX
    Explanations

    accountability and descriptive phrases

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

    list items or descriptions

    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
    ש
    0.54
    湆
    0.54
    نہ
    0.51
    荕
    0.51
    莯
    0.49
     apostolic
    0.49
    ელის
    0.49
    쎌
    0.48
    蠟
    0.47
    漾
    0.47
    POSITIVE LOGITS
    rá
    0.57
    .
    0.48
     Accountability
    0.44
     জরুরী
    0.44
     accountable
    0.44
    .”
    0.44
    hound
    0.44
    ro
    0.43
    ।
    0.43
    .’
    0.43
    Activations Density 0.000%

    No Known Activations