© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2295
    Prev
    Next
    INDEX
    Explanations

    CLI Output

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

    The neuron is attuned to technical‐document metadata and markup tokens—things like comment delimiters (//, /), version labels (“Version”), uppercase identifiers and headers (“Cisco,” “Systems,” “CLI,” “Output,” “Nos”), and similar structural markers.

    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
    cythe
    -0.82
     القرآن
    -0.76
     Delivery
    -0.71
    న
    -0.70
     самым
    -0.69
     wymaga
    -0.69
    Each
    -0.68
     Each
    -0.68
    Box
    -0.67
     even
    -0.66
    POSITIVE LOGITS
    versch
    0.90
     déjà
    0.87
    chrän
    0.87
     miroir
    0.84
    quantidade
    0.84
     tecnológicos
    0.83
    撤退
    0.83
     actuelles
    0.83
    Xr
    0.83
     rekke
    0.83
    Activations Density 0.001%

    No Known Activations