© 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. 93409
    Prev
    Next
    INDEX
    Explanations

    senior precision rotary

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

    The neuron detects descriptions of a vehicle malfunction or breakdown occurring during driving.

    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
     interesantes
    -1.31
    啐
    -1.27
     yeri
    -1.26
     you
    -1.25
     včetně
    -1.21
    你的
    -1.20
     sizin
    -1.19
     prazer
    -1.16
     your
    -1.16
     custos
    -1.13
    POSITIVE LOGITS
     this
    1.70
    ַּ
    1.46
     numerous
    1.35
     previous
    1.31
     damski
    1.26
     Consumers
    1.23
    댄
    1.23
    ּוֹ
    1.20
     several
    1.19
     stated
    1.19
    Activations Density 0.006%

    No Known Activations