© 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. 22-GEMMASCOPE-RES-131K
    7. 68828
    Prev
    Next
    INDEX
    Explanations

    integrals and biological terms

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

    mathematical expressions and equations in LaTeX format.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron appears to remain inactive and does not detect any particular feature.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     that
    -2.22
     gången
    -1.75
    𖡼
    -1.70
     ensure
    -1.64
    luents
    -1.63
     even
    -1.63
    %)$
    -1.62
    ktionen
    -1.60
    ariConfig
    -1.57
     banyo
    -1.57
    POSITIVE LOGITS
    ’
    2.52
    ‘
    2.23
    ↵
    1.93
    {
    1.92
    \
    1.92
     …
    1.86
     terrific
    1.80
     exceedingly
    1.73
    </i>
    1.72
     
    1.69
    Activations Density 0.003%

    No Known Activations