© 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. 74688
    Prev
    Next
    INDEX
    Explanations

    operating systems and code

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

    The neuron fires on low-level C implementation details—system header includes and reserved/internal identifiers (e.g. names with leading/trailing double underscores and internal libc macros).

    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
     our
    -1.81
    zados
    -1.36
     bijna
    -1.33
     smartly
    -1.30
     thoughtfully
    -1.28
    Ế
    -1.27
    чия
    -1.22
     realizó
    -1.22
     vähän
    -1.22
    жнему
    -1.20
    POSITIVE LOGITS
    3
    1.51
    .
    1.36
    6
    1.35
    8
    1.35
    2
    1.18
    5
    1.16
    Considering
    1.16
    Additionally
    1.16
    4
    1.16
     Branca
    1.15
    Activations Density 0.171%

    No Known Activations