© 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. 105615
    Prev
    Next
    INDEX
    Explanations

    immunocytochemistry and monetization

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

    medical, technical, or specific topics

    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
    防
    0.51
    IB
    0.51
    ONG
    0.48
     tenían
    0.47
    in
    0.46
    감
    0.45
    פ
    0.45
    explique
    0.44
    ROC
    0.44
    dried
    0.44
    POSITIVE LOGITS
    鸮
    0.51
     sagittal
    0.51
     monologue
    0.49
     قاسمی
    0.48
    stration
    0.47
     kuni
    0.47
     cranial
    0.46
     speechSynthesis
    0.44
     brightness
    0.44
     مزید
    0.44
    Activations Density 0.000%

    No Known Activations