© 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. 66661
    Prev
    Next
    INDEX
    Explanations

    challenging or negative qualities

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

    The neuron activates on highly subjective, emotionally charged descriptive words (especially intense adjectives and evaluative nouns).

    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
     marinho
    -0.99
    entown
    -0.98
     общения
    -0.95
    vensko
    -0.95
    誕生
    -0.93
                       
    -0.88
    itoriale
    -0.87
    வும்
    -0.86
    就业
    -0.86
    affaires
    -0.86
    POSITIVE LOGITS
     but
    1.66
    へ行
    1.03
     gorgeous
    1.03
     wonderful
    1.00
     pData
    0.98
     GOOD
    0.97
    '<
    0.97
     distinción
    0.96
     porém
    0.96
     dėl
    0.93
    Activations Density 0.088%

    No Known Activations