© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41507
    Prev
    Next
    INDEX
    Explanations

    risk factor for

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

    words or phrases that indicate a reason, cause, factor, or way for something to happen.

    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_10/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
    汌
    -2.66
    瞜
    -2.50
    笮
    -2.25
    鹪
    -2.20
     rü
    -2.20
     glisser
    -2.20
     étan
    -2.14
     aleación
    -2.13
     caucho
    -2.11
    夘
    -2.09
    POSITIVE LOGITS
     for
    7.50
     of
    3.47
     to
    2.98
     was
    2.27
    of
    1.88
     on
    1.88
    In
    1.84
    '
    1.79
    "
    1.77
    就是
    1.77
    Activations Density 0.703%

    No Known Activations