© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 53956
    Prev
    Next
    INDEX
    Explanations

    personal accounts and positive experiences

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

    This neuron detects first-person expressions of enjoyment or enthusiasm (e.g. “I love…,” “we get to…”).

    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
     will
    -1.26
    structors
    -1.23
    dieu
    -1.13
    ૬
    -1.10
     would
    -1.09
     parseFrom
    -1.01
    ditionally
    -1.00
     vendedores
    -1.00
    ૫
    -0.99
     CERTIFICATE
    -0.98
    POSITIVE LOGITS
     my
    1.27
     I
    1.27
     často
    1.22
     иногда
    1.18
    了一眼
    1.16
     working
    1.16
     TRABAJO
    1.13
     rewarding
    1.11
     particulières
    1.09
     clients
    1.09
    Activations Density 0.034%

    No Known Activations