© 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. 58655
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of people

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

    The neuron fires on subjective evaluation terms—especially descriptive adjectives or adverbs expressing appraisal (e.g. “acceptable,” “adorable,” “oddly”).

    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
    openzeppelin
    -0.85
    uyez
    -0.81
    omores
    -0.80
    久
    -0.78
    feri
    -0.78
    ᚄ
    -0.77
     метров
    -0.76
     APO
    -0.76
    ificent
    -0.75
    chown
    -0.75
    POSITIVE LOGITS
     lik
    2.98
     lovable
    2.27
    Lik
    1.99
    lik
    1.79
     Lik
    1.73
     endearing
    1.59
     attractive
    1.56
     liked
    1.52
    น่า
    1.42
     relatable
    1.34
    Activations Density 0.032%

    No Known Activations