© 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. 34-GEMMASCOPE-RES-131K
    7. 94006
    Prev
    Next
    INDEX
    Explanations

    copyright notices and code snippets

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

    This neuron responds to programming‐style annotation and comment markers (e.g. “@”, “///”, “#”), braces (“{” “}”), and similar code‐metadata tokens.

    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
    erstein
    -0.85
    abelle
    -0.78
    оп
    -0.74
    žius
    -0.74
     juos
    -0.73
    mouthed
    -0.71
    ieri
    -0.69
    forum
    -0.67
     corridors
    -0.66
    csd
    -0.65
    POSITIVE LOGITS
    Ephe
    0.69
     tsar
    0.67
     mại
    0.67
     Isidro
    0.67
     pyl
    0.67
    isInitialized
    0.66
     コミック
    0.66
     dialami
    0.65
    collant
    0.65
     cek
    0.64
    Activations Density 0.066%

    No Known Activations