© 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. 976
    Prev
    Next
    INDEX
    Explanations

    rpc, frozen, union, tritium, Hey, creep, Tab, rally, IP

    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
     who
    -1.44
     what
    -1.34
     :
    
    -1.32
    ̏
    -1.26
    ęć
    -1.21
    ↵↵
    -1.18
    /";
    -1.18
     miejscowości
    -1.16
    plained
    -1.15
     хорошее
    -1.15
    POSITIVE LOGITS
    </i>
    1.40
    ----------------
    1.30
    They
    1.28
    <b>
    1.25
    內容簡介
    1.23
    <i>
    1.23
     وذلك
    1.19
    								
    1.19
    <u>
    1.16
    println
    1.16
    Activations Density 0.079%

    No Known Activations