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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22354
    Prev
    Next
    INDEX
    Explanations

    summarizing text

    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_40_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
     වී
    0.43
    gy
    0.39
     narod
    0.39
     ጎ
    0.38
    ensory
    0.38
     rectilinear
    0.38
     धनु
    0.38
    ഞ്ഞു
    0.38
     fotos
    0.37
    ಙ
    0.37
    POSITIVE LOGITS
     Summar
    0.84
     summaries
    0.79
     summar
    0.77
     summarizing
    0.77
    Summar
    0.76
     summarize
    0.73
    summar
    0.70
     summarizes
    0.68
     summary
    0.66
     summarized
    0.65
    Activations Density 0.005%

    No Known Activations