© 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. 31332
    Prev
    Next
    INDEX
    Explanations

    words related to experience

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

    The neuron spots evaluative terms and phrases describing the quality of an “experience” (e.g. user experience, patient experience, fan experience), especially positive or negative adjectives like “superior,” “poor,” or “best.”

    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
    llä
    -0.82
    ligence
    -0.77
    lês
    -0.76
    secution
    -0.75
     бро
    -0.75
    Ikr
    -0.75
    صاص
    -0.75
    GIUM
    -0.75
    ówka
    -0.74
    riller
    -0.74
    POSITIVE LOGITS
     experience
    7.13
    experience
    5.16
     experiencia
    4.66
     experiences
    4.66
    Experience
    4.53
     Experience
    4.47
     EXPERIENCE
    4.22
     experiência
    4.09
    体验
    3.67
     expérience
    3.63
    Activations Density 0.107%

    No Known Activations