© 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. 130742
    Prev
    Next
    INDEX
    Explanations

    TV sets, workstations, projects

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

    tv mounts and wheels

    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
    萝
    0.48
    優先
    0.42
    Melitaea
    0.39
    ือก
    0.39
     alkal
    0.39
     Stras
    0.38
     варто
    0.38
     merito
    0.38
    aság
    0.38
    茲
    0.38
    POSITIVE LOGITS
     coursework
    0.52
     syllabus
    0.46
     exam
    0.44
    💻
    0.44
    papers
    0.43
    syllabus
    0.43
     Presentations
    0.41
     universitaria
    0.41
     ലാ
    0.41
     домой
    0.40
    Activations Density 0.073%

    No Known Activations