© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128177
    Prev
    Next
    INDEX
    Explanations

    operating system names

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

    The neuron fires on all‐caps identifiers and acronyms (e.g. constant names like AF_APPLE, CCITT, CHAOS, SPDX, BLUETOOTH, Unicode block labels, build tags, version numbers, etc.).

    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
     these
    -1.68
    同上
    -1.68
     habt
    -1.65
     about
    -1.61
     this
    -1.55
     mentioned
    -1.51
     involved
    -1.50
     when
    -1.48
     it
    -1.45
     gibts
    -1.42
    POSITIVE LOGITS
    If
    1.93
    Each
    1.72
     بعد
    1.65
     اگر
    1.63
    if
    1.62
     seperti
    1.61
     många
    1.60
    What
    1.59
     réjou
    1.58
    Whether
    1.55
    Activations Density 0.103%

    No Known Activations