© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11372
    Prev
    Next
    INDEX
    Explanations

    content sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    overlapping
    0.40
     tweet
    0.37
    豪
    0.37
    characteristics
    0.36
     summarise
    0.36
    complexity
    0.36
    summar
    0.36
     slang
    0.35
    히
    0.35
    DSL
    0.35
    POSITIVE LOGITS
     section
    1.83
     sections
    1.77
     sección
    1.59
    section
    1.52
     secciones
    1.52
     sezione
    1.48
     Section
    1.46
    sections
    1.44
    Section
    1.43
     seção
    1.41
    Activations Density 0.296%

    No Known Activations