© 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. 80084
    Prev
    Next
    INDEX
    Explanations

    time, initial, corner, you, of, known, used, to, Names

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

    shapes, angles, properties

    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
    coral
    0.55
    seab
    0.53
    >";
    0.52
    ían
    0.51
     incó
    0.51
    সম্প্র
    0.49
     umożliw
    0.49
     aren
    0.49
    zona
    0.49
     omoguć
    0.48
    POSITIVE LOGITS
    ocytosis
    0.46
     https
    0.45
    不斷
    0.43
     installer
    0.43
     installers
    0.42
    好
    0.42
    ৃষ্ট
    0.42
    不断
    0.41
    一套
    0.40
     stolen
    0.40
    Activations Density 0.001%

    No Known Activations