© 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. 104540
    Prev
    Next
    INDEX
    Explanations

    hypertension obese muscular hepatic

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

    tracking information updates

    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
     Tierra
    0.46
    。《
    0.45
    螅
    0.44
     Gaia
    0.44
     odyssey
    0.43
     неви
    0.42
     диапа
    0.42
    掍
    0.40
     wier
    0.40
    回復
    0.39
    POSITIVE LOGITS
     neutrophil
    0.52
     hypertension
    0.52
     obese
    0.49
     hypertensive
    0.49
     sulphate
    0.49
     muscular
    0.47
     graisse
    0.47
     whitish
    0.46
     huyết
    0.46
     hepatic
    0.46
    Activations Density 0.001%

    No Known Activations