© 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. 10-GEMMASCOPE-RES-131K
    4. 60891
    Prev
    Next
    INDEX
    Explanations

    pleading, needs, could have, gonna

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

    The neuron flags strongly emotional or urgent words and phrases—especially pleas, expressions of fear, or high‐intensity emotional language.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Öffnungszeiten
    -1.66
    Lets
    -1.62
    ならば
    -1.59
     regulación
    -1.52
     geheim
    -1.49
     connais
    -1.48
     heilige
    -1.48
     utiliser
    -1.45
     Erkrank
    -1.45
     favoriser
    -1.45
    POSITIVE LOGITS
     you
    1.77
     this
    1.76
    :'',
    1.73
     investiga
    1.61
    );
    1.59
     as
    1.59
     Polri
    1.57
     three
    1.56
     spesies
    1.52
     reaf
    1.51
    Activations Density 0.033%

    No Known Activations