© 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. 79023
    Prev
    Next
    INDEX
    Explanations

    Good Morning America

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

    The neuron fires on polite time-of-day greetings (e.g. “Good morning,” “Good evening,” 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_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
     inspection
    -0.68
    AVX
    -0.67
     pł
    -0.66
     impound
    -0.66
    Overlap
    -0.66
    𝓷
    -0.66
    ريقيا
    -0.65
    バトル
    -0.65
     electronics
    -0.64
     Electronics
    -0.63
    POSITIVE LOGITS
     Hos
    0.74
    apr
    0.72
     qq
    0.71
    mainan
    0.69
     Abre
    0.69
    ikko
    0.65
    mbs
    0.65
     Pikachu
    0.64
     במקום
    0.64
     Vivi
    0.63
    Activations Density 0.062%

    No Known Activations