© 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. 144288
    Prev
    Next
    INDEX
    Explanations

    foreign words and code snippets

    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
    State
    0.45
    uries
    0.44
    退出
    0.42
     hydroly
    0.41
     fig
    0.41
    Output
    0.40
    ᄀ
    0.40
    婊
    0.40
     تھی
    0.39
    チェ
    0.39
    POSITIVE LOGITS
     රස
    0.54
    idão
    0.51
    низу
    0.51
    harmed
    0.50
     Conselho
    0.50
    ătoare
    0.50
     morte
    0.49
    öyle
    0.48
     Clube
    0.47
     ইরানের
    0.47
    Activations Density 0.000%

    No Known Activations