© 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. 148904
    Prev
    Next
    INDEX
    Explanations

    components or materials

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

    table formatting

    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
    有關
    0.50
     沒有
    0.50
    拉斯
    0.46
     Biotechn
    0.46
    视野
    0.45
    梩
    0.45
     Uyg
    0.44
    тельство
    0.44
     nikdy
    0.44
     Waterfront
    0.44
    POSITIVE LOGITS
    м
    0.61
     panels
    0.50
    م
    0.50
    channels
    0.49
     units
    0.45
     channels
    0.45
    سٹر
    0.45
    lers
    0.44
    units
    0.44
     internals
    0.43
    Activations Density 0.000%

    No Known Activations