© 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. 34-GEMMASCOPE-RES-131K
    7. 31443
    Prev
    Next
    INDEX
    Explanations

    nick names from future literals

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

    The neuron is strongly activated by technical computing and hardware/software terms (e.g. device names, protocols, server/software components).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Domic
    -0.82
    ancestor
    -0.79
    helping
    -0.77
    mjs
    -0.77
    usertype
    -0.75
    配
    -0.75
    jms
    -0.75
     mensen
    -0.75
    づらい
    -0.74
    livejournal
    -0.74
    POSITIVE LOGITS
    Album
    0.93
     Tidal
    0.92
     albums
    0.87
     album
    0.86
    Server
    0.86
     Valence
    0.86
    LOCAL
    0.85
    SERVER
    0.84
     Ona
    0.84
     Squeeze
    0.83
    Activations Density 0.010%

    No Known Activations