© 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. 57717
    Prev
    Next
    INDEX
    Explanations

    international or foreign language elements

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

    version, displayName, nationality, other

    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
    縮
    0.45
     quilting
    0.44
    อบคุณ
    0.43
     سرطان
    0.43
    㓶
    0.43
    Tri
    0.42
    อกาส
    0.42
    無線
    0.42
     গ্রামবাস
    0.42
    </strong>
    0.41
    POSITIVE LOGITS
    ிகள்
    0.47
     innych
    0.44
    ຫຼາຍ
    0.44
     josé
    0.44
    -
    0.43
     altre
    0.42
    лама
    0.42
    दारों
    0.41
     иных
    0.40
    সাব
    0.40
    Activations Density 0.000%

    No Known Activations