© 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. 4263
    Prev
    Next
    INDEX
    Explanations

    international place names

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

    foreign languages and numbers

    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
    ்கு
    0.42
    ⺊
    0.40
    ர்க
    0.38
     ईश्वर
    0.37
     &\
    0.36
     laborator
    0.36
    䚯
    0.36
    ⵥ
    0.36
    ⵍ
    0.36
     Déc
    0.36
    POSITIVE LOGITS
     asimismo
    0.46
     हिंदुस्तान
    0.45
     indonesia
    0.43
     españa
    0.42
    한테
    0.42
     nigeria
    0.41
     Casino
    0.39
    một
    0.39
     casino
    0.38
     Cbd
    0.38
    Activations Density 1.213%

    No Known Activations