© 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. 22-GEMMASCOPE-RES-131K
    7. 38645
    Prev
    Next
    INDEX
    Explanations

    biological and scientific terms

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

    the first 3-4 letters of scientific or technical terminology, particularly in medical and engineering contexts.

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

    The neuron strongly activates on the very first (capitalized) token of new sections or sentences.

    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
    gencias
    -1.41
     buvo
    -1.39
    。
    -1.32
    Dota
    -1.29
    TryDecode
    -1.29
     macam
    -1.24
     —
    -1.22
    étaro
    -1.21
     tivesse
    -1.20
    ugía
    -1.18
    POSITIVE LOGITS
    ,
    1.59
    ’
    1.48
    りゃ
    1.42
    сль
    1.38
     Chinois
    1.34
     vertellen
    1.34
    {
    1.34
     financières
    1.33
     veranderen
    1.33
    -
    1.32
    Activations Density 0.103%

    No Known Activations