© 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. 46824
    Prev
    Next
    INDEX
    Explanations

    well, nicely, greatly, heavily, poorly

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

    widely available

    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
    م
    0.58
    ル
    0.57
     ليس
    0.55
    ﺮ
    0.54
    м
    0.54
    BREAK
    0.53
     غير
    0.52
     非
    0.52
     BREAK
    0.52
    ルイ
    0.52
    POSITIVE LOGITS
    -
    0.64
    ate
    0.57
    az
    0.54
     worded
    0.54
     genutzt
    0.53
     applauded
    0.53
    ileged
    0.52
     financed
    0.52
     tolerated
    0.51
    ä
    0.51
    Activations Density 0.080%

    No Known Activations