© 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. 158954
    Prev
    Next
    INDEX
    Explanations

    medical conditions and specific terms

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

    order and receipt or visit

    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
    Cook
    0.43
     ഈ
    0.43
    CBC
    0.43
    🗓
    0.40
    [^
    0.39
    Synopsis
    0.39
     कोणत्याही
    0.39
     कोऑ
    0.39
     reigning
    0.38
    இந்தப்
    0.38
    POSITIVE LOGITS
    ли
    0.60
    кл
    0.54
     przestr
    0.52
    рон
    0.49
    usstsein
    0.48
    antaranya
    0.48
    HttpPut
    0.47
    屑
    0.47
     antaranya
    0.47
     REACT
    0.47
    Activations Density 0.000%

    No Known Activations