© 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. 65922
    Prev
    Next
    INDEX
    Explanations

    serine/threonine kinase

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

    forward slashes followed by a single character, especially in technical or path-like contexts.

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

    This neuron responds specifically to the letter “s” when it occurs immediately after a slash (i.e. “/s” sequences).

    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
     Saltar
    -2.36
     ingrained
    -2.23
     striving
    -2.23
     longstanding
    -2.14
     Campeonato
    -2.09
     بسیار
    -2.09
     strives
    -2.08
     kuitenkin
    -2.08
     strive
    -2.06
    هب
    -2.06
    POSITIVE LOGITS
     of
    2.98
    2
    2.55
     fünf
    2.33
     revamped
    2.28
     zwölf
    2.23
     overly
    2.19
     dismal
    2.19
     immense
    2.19
     sechs
    2.17
     exceptionally
    2.16
    Activations Density 0.003%

    No Known Activations