© 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. 10-GEMMASCOPE-RES-131K
    7. 129775
    Prev
    Next
    INDEX
    Explanations

    subscripts like H$_2$ or $A_2$

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

    numerical subscripts in mathematical notation.

    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
    Despite
    -3.13
    This
    -3.02
    Although
    -2.83
    Though
    -2.81
    They
    -2.81
    There
    -2.52
    Surprisingly
    -2.47
    However
    -2.42
    While
    -2.42
    Since
    -2.38
    POSITIVE LOGITS
    ⚣
    2.80
    '
    2.66
    蠖
    2.55
    箧
    2.50
     travailler
    2.50
    騭
    2.33
    袛
    2.30
     déterminer
    2.30
    ⩖
    2.28
    
    2.27
    Activations Density 0.019%

    No Known Activations