Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8792
    Prev
    Next
    INDEX
    Explanations

    food, travel, and entertainment recommendations

    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
     concerning
    0.38
    Referring
    0.37
    hereafter
    0.37
     존재하는
    0.36
     arisen
    0.35
     commonly
    0.34
     inescap
    0.34
     pathogenesis
    0.33
    ♘
    0.33
     hereafter
    0.33
    POSITIVE LOGITS
     красиво
    0.46
     bellissimo
    0.46
     odlič
    0.45
    素晴らしい
    0.42
     великолеп
    0.42
     rất
    0.42
     beautifully
    0.42
    不錯
    0.41
     Excellent
    0.41
    性价比
    0.40
    Activations Density 0.021%

    No Known Activations