© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 25225
    Prev
    Next
    INDEX
    Explanations

    anger, rage, prejudice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reassuring
    0.45
    weak
    0.44
    embedding
    0.43
    魅
    0.43
     illusion
    0.41
    暧
    0.41
    झाने
    0.40
     concat
    0.40
     strange
    0.39
    惴
    0.39
    POSITIVE LOGITS
     anger
    2.34
     angry
    2.13
     Anger
    1.99
    愤怒
    1.95
     rage
    1.90
    怒
    1.89
     angrily
    1.85
     Angry
    1.85
     colère
    1.80
    Angry
    1.77
    Activations Density 0.003%

    No Known Activations