© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211891
    Prev
    Next
    INDEX
    Explanations

    specialized contexts

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

    medical ontology terms

    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
    Negative Logits
     mankind
    0.46
     membro
    0.43
    );
    0.42
    )_
    0.42
     isometry
    0.41
     fermions
    0.40
     específicas
    0.40
    BinaryOperation
    0.40
    श्विक
    0.40
     logarithms
    0.40
    POSITIVE LOGITS
     तुझे
    0.55
     Ս
    0.54
    栥
    0.50
     Жи
    0.50
     ఉంటు
    0.49
     সম্মত
    0.49
    bathtub
    0.48
     सर्विस
    0.48
     तुझ्या
    0.48
     トート
    0.47
    Activations Density 0.000%

    No Known Activations