© 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. 55211
    Prev
    Next
    INDEX
    Explanations

    vegetarian dishes, acidic side

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

    non-traditional, not, startup, german, gibberish

    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
    کرا
    0.44
     Statutes
    0.42
    स्तो
    0.39
    ，
    0.39
     statutes
    0.39
     parallax
    0.39
    ورا
    0.38
    وروب
    0.37
     vair
    0.37
     dels
    0.37
    POSITIVE LOGITS
     조금
    0.43
    direction
    0.43
    一篇
    0.43
     ឬ
    0.42
     কিংবা
    0.42
    webserv
    0.42
     কম্পিউটার
    0.41
     senere
    0.40
    weight
    0.40
    もしくは
    0.40
    Activations Density 0.000%

    No Known Activations