© 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. 16-GEMMASCOPE-2-RES-262K
    7. 20687
    Prev
    Next
    INDEX
    Explanations

    sandwich combinations

    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_16_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
     a
    1.20
    nya
    1.01
    S
    1.01
    se
    0.98
     .
    0.93
     -
    0.91
    ne
    0.88
     ,
    0.88
     The
    0.87
    m
    0.87
    POSITIVE LOGITS
    ת
    0.86
    тру
    0.84
     devra
    0.81
    ذج
    0.80
     expliquer
    0.77
    ائي
    0.77
    ຫາ
    0.77
    ურთი
    0.77
    ائح
    0.76
    ю
    0.76
    Activations Density 0.002%

    No Known Activations