© 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. 96105
    Prev
    Next
    INDEX
    Explanations

    DK yarn or no VIP

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

    medical terminology

    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
    嗽
    0.44
    ally
    0.43
    rafish
    0.43
    佂
    0.42
    月的
    0.42
    ða
    0.42
    стя
    0.41
    ɪ
    0.41
     Got
    0.41
     nightly
    0.41
    POSITIVE LOGITS
    ...</
    0.48
    了一個
    0.46
    ഒരു
    0.46
    षित
    0.45
     گرو
    0.44
     これは
    0.43
     prati
    0.43
     സമൂ
    0.43
    これは
    0.42
     μετά
    0.42
    Activations Density 0.000%

    No Known Activations