© 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. 70364
    Prev
    Next
    INDEX
    Explanations

    medical, scientific, or foreign terms

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

    counting, summing, domain, legal, pediatric

    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
    אר
    0.50
    <0xD6>
    0.48
    ди
    0.48
     impossibility
    0.47
    גים
    0.47
    ጥረ
    0.46
    𝔬
    0.46
    Funcion
    0.46
     הר
    0.45
    ט
    0.45
    POSITIVE LOGITS
     Pediatric
    0.47
     pediatric
    0.45
     epidemiological
    0.44
     kennen
    0.43
    ὺς
    0.43
     Epidemi
    0.42
     famosa
    0.42
     belangrijke
    0.41
     memastikan
    0.40
    進行
    0.40
    Activations Density 0.000%

    No Known Activations