© 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. 194520
    Prev
    Next
    INDEX
    Explanations

    numbers and words like observed, bridge, in, used

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

    handling choices and questions

    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
    の内
    0.50
     innermost
    0.47
     Orte
    0.47
     Ș
    0.47
     Бі
    0.47
     Ş
    0.47
     König
    0.47
     iç
    0.46
     Аль
    0.46
    ısı
    0.46
    POSITIVE LOGITS
     ?>
    0.42
    انب
    0.42
    fst
    0.42
    ة
    0.42
    嗓
    0.42
    ans
    0.40
    myapp
    0.40
    閇
    0.40
    >(
    0.40
     nationally
    0.40
    Activations Density 0.000%

    No Known Activations