© 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. 35322
    Prev
    Next
    INDEX
    Explanations

    first advent, gray fabrics, not only

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

    similarity and regions

    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
    昛
    0.59
    ে
    0.52
     ಮೂಲಕ
    0.52
     Remains
    0.52
    मूर्ति
    0.49
     또한
    0.48
     குடியிருப்ப
    0.47
     comprendere
    0.47
    ၏
    0.47
     Travels
    0.46
    POSITIVE LOGITS
     valid
    0.47
     lib
    0.47
     yellow
    0.46
    <unused60>
    0.46
     O
    0.46
     label
    0.46
     lab
    0.45
     letter
    0.45
     typeface
    0.44
     isso
    0.44
    Activations Density 0.000%

    No Known Activations