© 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. 767
    Prev
    Next
    INDEX
    Explanations

    introducing details

    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
    ולוג
    0.47
    बाईल
    0.45
    symmetric
    0.44
    ל
    0.43
     propi
    0.42
    יש
    0.42
    л
    0.41
     disgust
    0.41
    день
    0.40
    বিনোদন
    0.40
    POSITIVE LOGITS
     সাল
    0.52
    ="
    0.51
     这里
    0.49
     p
    0.48
     Digestive
    0.46
     langt
    0.45
     erő
    0.45
     ব
    0.45
    of
    0.44
     ope
    0.44
    Activations Density 0.000%

    No Known Activations