© 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-262K
    7. 112784
    Prev
    Next
    INDEX
    Explanations

    coffee bug

    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
     quenched
    0.42
     vudd
    0.42
    ito
    0.42
     authentic
    0.42
    acam
    0.42
     divul
    0.42
    \
    0.42
     entr
    0.41
     dispersed
    0.41
     Ordin
    0.41
    POSITIVE LOGITS
    ק
    0.50
    काच्या
    0.46
    тную
    0.46
    塑料
    0.45
    嘆
    0.44
     있으면
    0.43
    え
    0.43
    电影
    0.43
    惘
    0.43
    שו
    0.42
    Activations Density 0.016%

    No Known Activations