© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110530
    Prev
    Next
    INDEX
    Explanations

    Socrates, Twitter, Guardia Civil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    льзу
    0.49
    事実
    0.48
    ть
    0.48
    ))%>%
    0.47
    ш
    0.47
    шь
    0.46
    сть
    0.45
     činjen
    0.45
     CIN
    0.43
    ン
    0.42
    POSITIVE LOGITS
     aldı
    0.50
     తాగ
    0.49
     hanged
    0.49
    gató
    0.48
    arına
    0.48
    arı
    0.47
     prevail
    0.47
     çıktı
    0.47
     Sphere
    0.46
     prevails
    0.46
    Activations Density 0.005%

    No Known Activations