© 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. 4207
    Prev
    Next
    INDEX
    Explanations

    dislike

    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
    差
    0.38
    Name
    0.37
    NaOH
    0.36
    包含
    0.35
    memcpy
    0.35
     adsorption
    0.34
     watermark
    0.34
    Size
    0.34
    timestamp
    0.34
     assay
    0.34
    POSITIVE LOGITS
    苦手
    0.95
    不喜欢
    0.90
     싫
    0.79
     dislike
    0.79
    싫
    0.77
     dislikes
    0.77
     disliked
    0.73
     distaste
    0.71
     aversion
    0.69
    讨厌
    0.68
    Activations Density 0.091%

    No Known Activations