© 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. 16-GEMMASCOPE-2-RES-262K
    7. 144407
    Prev
    Next
    INDEX
    Explanations

    multilingual and special characters

    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_16_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
    ي
    1.27
    י
    1.26
    ת
    1.01
    ে
    0.86
    edik
    0.83
    드
    0.82
     שה
    0.81
    ש
    0.80
    iere
    0.78
    ፣
    0.77
    POSITIVE LOGITS
    s
    1.23
    ificant
    0.78
    ための
    0.75
    ates
    0.75
    BEL
    0.73
    о
    0.73
    um
    0.70
     उपयोग
    0.70
     которому
    0.70
     गट
    0.70
    Activations Density 0.001%

    No Known Activations