© 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. 143355
    Prev
    Next
    INDEX
    Explanations

    counting sequence numbers

    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
     Sheng
    0.39
     retali
    0.38
     جائز
    0.38
     سنت
    0.38
     зни
    0.37
    こともある
    0.37
    zina
    0.37
    飡
    0.37
     प्यारी
    0.37
     bab
    0.36
    POSITIVE LOGITS
    段
    0.47
    second
    0.43
     offsets
    0.41
     midway
    0.40
    OFFSET
    0.40
    cumsum
    0.39
     段
    0.39
     seg
    0.38
     footballers
    0.38
     totalled
    0.38
    Activations Density 0.073%

    No Known Activations