© 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. 119796
    Prev
    Next
    INDEX
    Explanations

    in fact / in reality / in order

    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
     in
    -2.42
     by
    -2.36
     only
    -2.28
     on
    -2.14
     it
    -2.11
     there
    -2.11
     solely
    -1.95
     eleven
    -1.88
     because
    -1.88
     or
    -1.88
    POSITIVE LOGITS
     consente
    2.28
    苼
    2.22
    戽
    2.19
    豳
    2.05
    がこの
    2.02
    蛱
    2.02
    
    1.95
    gives
    1.91
    ſa
    1.91
    驁
    1.89
    Activations Density 0.037%

    No Known Activations