© 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. 101360
    Prev
    Next
    INDEX
    Explanations

    therapies for chronic neurologic disorders

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

    punctuation and separators

    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
     //.
    0.46
    ت
    0.45
    upe
    0.45
    vý
    0.44
    βε
    0.44
     έ
    0.43
    Decoding
    0.43
    ⩽
    0.43
    Search
    0.42
    Mé
    0.41
    POSITIVE LOGITS
     provincia
    0.50
     tyrant
    0.50
     statesman
    0.47
     consac
    0.46
    礁
    0.46
     roku
    0.45
     MAINT
    0.45
     idiom
    0.45
     година
    0.45
     defunct
    0.45
    Activations Density 0.000%

    No Known Activations