© 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. 182403
    Prev
    Next
    INDEX
    Explanations

    medical and disease terms

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

    measuring quantities or states

    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
    에
    0.62
     비슷한
    0.47
    akta
    0.47
    ริกา
    0.46
     주인
    0.44
    bilt
    0.44
    asim
    0.44
     તેણી
    0.44
    특별시
    0.43
     ቦ
    0.43
    POSITIVE LOGITS
     doença
    0.47
     vorg
    0.45
     vor
    0.45
     doenças
    0.45
     enfermedades
    0.44
    ophages
    0.44
    ោធ
    0.44
     inflammatory
    0.44
    errno
    0.43
     immunosupp
    0.43
    Activations Density 0.002%

    No Known Activations