© 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. 31-GEMMASCOPE-2-RES-262K
    7. 44524
    Prev
    Next
    INDEX
    Explanations

    mood and atmosphere

    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_31_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
     Exchange
    0.44
     単
    0.42
     Direct
    0.40
     exchange
    0.39
    try
    0.39
     img
    0.39
     '
    0.38
    exchange
    0.38
    edere
    0.38
     directed
    0.38
    POSITIVE LOGITS
    褻
    0.55
    ဖို့
    0.48
    ين
    0.45
    罍
    0.43
    Wasser
    0.42
    咫
    0.42
    罄
    0.42
     ristorante
    0.41
     أبريل
    0.41
    ơi
    0.41
    Activations Density 0.000%

    No Known Activations