© 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. 22-GEMMASCOPE-RES-131K
    4. 15231
    Prev
    Next
    INDEX
    Explanations

    available now or today

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

    The neuron strongly activates on imperative calls-to-action in marketing or ads (e.g. “Find…,” “Schedule your service now,” “Order yours now,” “Open a new account,” 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_22/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
    m
    -1.28
     banheiro
    -1.20
    𝑣
    -1.15
    Deep
    -1.14
     まる
    -1.11
    きら
    -1.10
    -1.09
     vano
    -1.09
    v
    -1.08
    sk
    -1.07
    POSITIVE LOGITS
     or
    2.05
     by
    1.97
     using
    1.55
     via
    1.49
     with
    1.48
     here
    1.46
     at
    1.38
     today
    1.38
     through
    1.29
     istimewa
    1.23
    Activations Density 0.035%

    No Known Activations