© 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. 3070
    Prev
    Next
    INDEX
    Explanations

    adding and combining

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

    The neuron fires strongly on list‐or step‐style signals—numbers, commas, hyphens, and connective words like “Then,” “Finally,” “add,” etc.—marking out an ordered, stepwise enumeration in the text.

    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
    },[])
    -0.92
    总之
    -0.90
     pulito
    -0.82
    ppm
    -0.81
     ám
    -0.81
     لأن
    -0.77
     péché
    -0.77
    𝘥
    -0.77
     crean
    -0.77
     jengibre
    -0.77
    POSITIVE LOGITS
     add
    4.88
     Add
    4.31
    Add
    4.31
    add
    3.88
     combine
    3.47
     Combine
    3.42
    Combine
    3.30
     coupled
    2.75
     combined
    2.70
    combine
    2.66
    Activations Density 0.063%

    No Known Activations