© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91655
    Prev
    Next
    INDEX
    Explanations

    expressions of pleasure and greeting

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

    The neuron fires on brief positive or friendly sentiment words—e.g. compliments (“Nice,” “love,” “work”) and greetings/appreciations (“glad,” “meet you”).

    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
     desirable
    -0.85
     MatDialog
    -0.85
     occurs
    -0.79
    小時
    -0.79
     exploration
    -0.79
     Relaciones
    -0.78
    телям
    -0.77
    NOUN
    -0.77
    وئ
    -0.77
     Säure
    -0.76
    POSITIVE LOGITS
    Nice
    1.56
     Nice
    1.47
     nice
    1.41
    nice
    1.20
    finally
    1.11
     наконец
    1.10
    NICE
    1.10
     NICE
    1.02
     finally
    0.98
     pleasure
    0.95
    Activations Density 0.010%

    No Known Activations