© 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. 231598
    Prev
    Next
    INDEX
    Explanations

    medical and development contexts

    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
    و
    0.61
    يرين
    0.54
     مليار
    0.52
    وف
    0.50
    ليو
    0.50
    يري
    0.49
    يريا
    0.49
    ViewGroup
    0.48
    ˨
    0.47
     hepatocellular
    0.47
    POSITIVE LOGITS
    bau
    0.50
    ண்டும்
    0.50
     किताब
    0.49
     RUD
    0.47
    ressant
    0.47
    pv
    0.47
    ın
    0.46
     کتاب
    0.45
    መ
    0.45
     पुस्तिका
    0.45
    Activations Density 0.000%

    No Known Activations