Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8179
    Prev
    Next
    INDEX
    Explanations

    Morrissey racial slur accusation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    entrant
    -0.90
    getSelection
    -0.85
    ﹤
    -0.81
    ुन
    -0.81
    &=&\
    -0.78
     Librarian
    -0.78
    楽曲
    -0.77
     Ślą
    -0.77
    插入
    -0.77
    towej
    -0.77
    POSITIVE LOGITS
     NUM
    0.84
    racia
    0.83
    vosti
    0.80
    ucar
    0.79
    wendigkeit
    0.79
    Ϲ
    0.78
    ådet
    0.78
    TacToe
    0.77
    Voir
    0.76
    Disney
    0.76
    Activations Density 0.000%

    No Known Activations