© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93043
    Prev
    Next
    INDEX
    Explanations

    science and technical articles

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

    titles of academic works such as books, journals, and symposia.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     your
    -1.08
     shouldn
    -1.05
    ologische
    -1.04
     wöch
    -1.03
    黉
    -1.01
    髕
    -1.01
     términos
    -1.00
     Politica
    -1.00
     الوح
    -0.99
     historian
    -0.98
    POSITIVE LOGITS
     収納
    1.03
     approaches
    0.97
    illoma
    0.95
     berbagai
    0.94
    Paste
    0.94
     the
    0.93
    METHODS
    0.91
     secas
    0.89
    กัน
    0.88
    Century
    0.87
    Activations Density 0.029%

    No Known Activations