© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81071
    Prev
    Next
    INDEX
    Explanations

    version mapping GUID

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

    The neuron fires on numeric literals—any standalone numbers (e.g. GUID segments, sizes, versions, 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_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
     SUSTAIN
    -0.75
     esquí
    -0.75
     woh
    -0.75
     sustainability
    -0.74
     Sustain
    -0.74
     sustains
    -0.73
     શ
    -0.73
     sustain
    -0.72
     Sandro
    -0.72
    aln
    -0.71
    POSITIVE LOGITS
     version
    1.03
     Version
    0.97
     versiones
    0.85
    DCE
    0.84
     MV
    0.82
    version
    0.82
     версии
    0.81
    ByVersion
    0.80
     RFC
    0.80
     KV
    0.79
    Activations Density 0.032%

    No Known Activations