© 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. 77224
    Prev
    Next
    INDEX
    Explanations

    gaining understanding and new perspectives

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

    The neuron flags passages where the author speaks in the first person or shares personal experience or reflection (e.g. “I…,” “helped me…,” “my daughter…,” “has made her think…”).

    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
    ține
    -1.08
    ettbewer
    -1.03
    lossen
    -1.02
     Ө
    -1.02
    𝑥
    -1.01
    теристи
    -0.98
     افتراض
    -0.97
    attractive
    -0.97
    lossing
    -0.95
     ligt
    -0.94
    POSITIVE LOGITS
     appreciation
    2.05
     clearer
    1.84
     better
    1.75
     renewed
    1.71
     appreciate
    1.70
     perspective
    1.62
     new
    1.57
     deeper
    1.53
     newfound
    1.51
     understand
    1.48
    Activations Density 0.037%

    No Known Activations