© 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. 50578
    Prev
    Next
    INDEX
    Explanations

    finding / education / CD

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

    performance optimization

    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
     Règ
    0.56
    בע
    0.48
    ྵ
    0.48
    완
    0.47
     Grèce
    0.47
     Screenshots
    0.47
    푅
    0.46
    𝓖
    0.46
     Jezus
    0.46
    лянчук
    0.46
    POSITIVE LOGITS
    ak
    0.59
    er
    0.56
    j
    0.52
     وتن
    0.51
    se
    0.51
    il
    0.50
    un
    0.50
    el
    0.50
    mik
    0.50
    ina
    0.49
    Activations Density 0.000%

    No Known Activations