© 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. 60855
    Prev
    Next
    INDEX
    Explanations

    hygiene or medical terms

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

    sections, lists, and context

    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
     impedance
    0.51
     denials
    0.50
     writable
    0.49
     користу
    0.49
     percorso
    0.49
     subroutine
    0.47
    ة
    0.47
    жні
    0.47
    ሳ
    0.46
     expr
    0.46
    POSITIVE LOGITS
    drav
    0.47
    jahteraan
    0.46
    helial
    0.45
    strual
    0.45
    giene
    0.44
    afin
    0.44
    amom
    0.43
    atherm
    0.43
     ମ
    0.43
     తల్లి
    0.43
    Activations Density 0.000%

    No Known Activations