© 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. 241350
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
    campo
    0.45
    ılık
    0.41
     beer
    0.40
    …
    0.40
    ज्ञान
    0.40
    基于
    0.40
     keterangan
    0.40
    ą
    0.40
    ør
    0.39
    தான்
    0.39
    POSITIVE LOGITS
     ܡ
    0.49
     セミ
    0.48
     Δια
    0.48
     doodles
    0.47
     ハート
    0.46
    旿
    0.46
     déplacements
    0.46
     背
    0.46
     معاہد
    0.46
     ഉപകരണ
    0.46
    Activations Density 0.001%

    No Known Activations