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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3404
    Prev
    Next
    INDEX
    Explanations

    bangers!, artist, shitstorm

    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_16k_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
    is
    0.59
    A
    0.58
    http
    0.54
    im
    0.53
    al
    0.53
    il
    0.51
    ام
    0.47
    é
    0.46
    o
    0.46
    C
    0.46
    POSITIVE LOGITS
    們
    0.65
     খ্যা
    0.64
     eatery
    0.61
     シャ
    0.61
    খ্যাত
    0.60
    般的
    0.60
     adore
    0.57
     單
    0.57
     フォー
    0.57
     unrivalled
    0.57
    Activations Density 0.386%

    No Known Activations