© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 7928
    Prev
    Next
    INDEX
    Explanations

    anger and frustration

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

    the presence of strong negative emotional or anger-related language indicating high emotional intensity.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    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
     Embedding
    0.44
     Spec
    0.42
    Spec
    0.42
     அதிசய
    0.42
    瞞
    0.41
    ייש
    0.40
    ifo
    0.39
     nanom
    0.39
    weak
    0.38
     چاندی
    0.38
    POSITIVE LOGITS
     anger
    2.23
     angry
    2.22
     angrily
    2.05
    愤怒
    1.94
     colère
    1.91
     गुस्से
    1.82
     enraged
    1.80
     Anger
    1.77
    怒
    1.77
     rage
    1.76
    Activations Density 0.069%

    No Known Activations