© 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. 99320
    Prev
    Next
    INDEX
    Explanations

    viagra and kamagra

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

    list items and descriptions

    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
    <0x0D>
    0.47
    </h3>
    0.45
    ’
    0.45
     Open
    0.44
    ↵
    0.43
     Re
    0.43
     G
    0.43
    此
    0.43
    <unused60>
    0.42
    ICC
    0.42
    POSITIVE LOGITS
    맇
    0.54
    대를
    0.49
    rägen
    0.49
     isomorphisms
    0.48
    edizione
    0.48
    otipo
    0.48
     Лей
    0.48
    erecht
    0.48
    㕵
    0.47
    hner
    0.46
    Activations Density 0.000%

    No Known Activations