© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72177
    Prev
    Next
    INDEX
    Explanations

    biological and technical terms

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

    scientific names and taxonomic terms including species names, biological compounds, and minerals.

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

    The neuron selectively activates on numeric tokens (numbers and numerical identifiers) in the text.

    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
     этих
    -1.16
     αυτά
    -1.02
     dessa
    -1.02
    這些
    -0.95
     которые
    -0.89
     forlorn
    -0.86
     said
    -0.85
    ondres
    -0.85
     estos
    -0.84
     Hoodie
    -0.84
    POSITIVE LOGITS
     at
    1.09
    韜
    0.94
     (
    0.92
    }])
    0.88
     representado
    0.88
     reassurance
    0.87
    enares
    0.85
    fcntl
    0.85
    鍒
    0.83
    ⁦
    0.82
    Activations Density 0.143%

    No Known Activations