© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 4
    Prev
    Next
    INDEX
    Explanations

    cygwin, Bari, Shiro, chara, Nani, Ghosh

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -2.75
    er
    -2.73
     nieruch
    -2.42
     miliardi
    -2.34
     realizará
    -2.30
    眎
    -2.30
     demands
    -2.27
    毯
    -2.20
    ’
    -2.17
    ,,,,
    -2.16
    POSITIVE LOGITS
    曁
    2.39
     "
    2.30
     バッジ
    2.27
    很赞
    2.19
    鉿
    2.19
    倻
    2.13
    鳙
    2.13
     abond
    2.11
    当下
    2.09
     huile
    2.08
    Activations Density 0.022%

    No Known Activations