© 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. 151159
    Prev
    Next
    INDEX
    Explanations

    trademark, domain name, stunning

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

    new modeexploit discrepancies

    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
    ativ
    0.52
     j
    0.50
    alk
    0.49
    in
    0.47
    نده
    0.47
     Jin
    0.47
    ش
    0.46
    sh
    0.46
    out
    0.46
    TOP
    0.46
    POSITIVE LOGITS
     број
    0.62
     didReceive
    0.59
     бага
    0.56
     министер
    0.56
     長財布
    0.56
     електрон
    0.55
     φωτογραφ
    0.55
     профи
    0.55
     биологи
    0.55
     фізи
    0.55
    Activations Density 0.000%

    No Known Activations