© 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. 4080
    Prev
    Next
    INDEX
    Explanations

    emotional expression and conflict

    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/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
    籵
    0.41
     interoper
    0.40
     refurbishment
    0.39
     gentlemen
    0.38
     manly
    0.38
    ソフトウェア
    0.38
     አገልግሎ
    0.38
     enterprise
    0.37
     सॉफ्टवेयर
    0.37
    輔
    0.37
    POSITIVE LOGITS
     unconsciously
    0.81
     dysfunctional
    0.73
     rumin
    0.71
     unconscious
    0.71
     emotionally
    0.70
     emotional
    0.67
     conductas
    0.64
     sabot
    0.64
     internalized
    0.64
     emocional
    0.63
    Activations Density 0.113%

    No Known Activations