© 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. 102298
    Prev
    Next
    INDEX
    Explanations

    genetic pathway promoter

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

    numerical dates or year references, particularly in document headers and citations.

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

    The neuron activates on tokens containing numbers or numeric values (including digits, floats, or mixed alphanumeric strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     wohnung
    -1.23
     tasarım
    -1.22
     templado
    -1.21
     decorativo
    -1.21
    Which
    -1.20
     húmedo
    -1.20
    If
    -1.19
    which
    -1.17
     zincir
    -1.17
    You
    -1.16
    POSITIVE LOGITS
     idée
    1.27
    ☰
    1.23
    dańsk
    1.22
     Longitudinal
    1.18
     difusión
    1.18
    ✱
    1.18
    ("'"
    1.17
     étude
    1.17
     incorporated
    1.17
     *}
    1.16
    Activations Density 0.175%

    No Known Activations