© 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. 41518
    Prev
    Next
    INDEX
    Explanations

    up the mountain

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

    linguistic profiling

    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
     استاذ
    0.57
     dostup
    0.52
     उपलब्ध
    0.50
     მაგრამ
    0.50
     pozn
    0.46
    讓我
    0.45
    ១
    0.45
    䛺
    0.45
     نادي
    0.44
     এম
    0.44
    POSITIVE LOGITS
    یده
    0.48
     derivatives
    0.41
    ್‌
    0.41
    +'-
    0.41
    嶅
    0.41
     clones
    0.40
    annonce
    0.40
     flame
    0.40
    اپ
    0.40
     transmissions
    0.39
    Activations Density 0.000%

    No Known Activations