© 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. 31215
    Prev
    Next
    INDEX
    Explanations

    starting processes

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

    The neuron activates strongly on CamelCase or capitalized action‐verb identifiers (e.g. StartUpdatingLocation, StopUpdatingLocation, OAuth2Authentication, start, finishAuthentication), i.e. on function/method names that begin with a verb in 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
     hatal
    -0.81
     keluar
    -0.79
    有两
    -0.76
     Configuración
    -0.75
     letto
    -0.75
     ση
    -0.73
    Hui
    -0.73
    ためには
    -0.73
     civic
    -0.73
     recent
    -0.73
    POSITIVE LOGITS
     recording
    1.19
     timer
    1.14
     or
    1.09
     listening
    1.08
    background
    1.07
    timer
    1.03
     monitoring
    1.02
     sesión
    1.02
     counting
    0.99
     session
    0.99
    Activations Density 0.029%

    No Known Activations