© 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. 93735
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

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

    The neuron is keyed to numeric tokens—i.e. it fires on numbers and numeric literals in the code.

    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
    sianic
    -0.66
     förb
    -0.66
     Stacey
    -0.65
    authorised
    -0.65
     entiendo
    -0.64
     ambao
    -0.64
     phosphoric
    -0.63
    Stacey
    -0.63
     FirebaseAuth
    -0.62
    nitrogen
    -0.62
    POSITIVE LOGITS
     Socket
    0.71
    Socket
    0.71
     декора
    0.71
    square
    0.71
    lication
    0.70
    result
    0.69
    poses
    0.69
    layout
    0.69
    loss
    0.69
     ancients
    0.68
    Activations Density 0.062%

    No Known Activations