© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35083
    Prev
    Next
    INDEX
    Explanations

    programming utilities and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SRA
    -0.77
    átek
    -0.75
     hostel
    -0.75
     proverb
    -0.73
     moron
    -0.73
     pizzeria
    -0.73
     TextEditing
    -0.72
    Gruss
    -0.72
    研究院
    -0.72
    NGL
    -0.71
    POSITIVE LOGITS
     alvor
    0.93
    Vä
    0.93
     død
    0.92
     incrível
    0.90
    хъ
    0.90
     réus
    0.90
    ឍ
    0.88
     you
    0.87
    ‌های
    0.86
    rifying
    0.86
    Activations Density 0.090%

    No Known Activations