© 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. 123525
    Prev
    Next
    INDEX
    Explanations

    not sure that

    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
    ならでは
    -1.77
    鯡
    -1.73
    
    -1.66
    hopefully
    -1.63
     tristes
    -1.63
    Siti
    -1.60
    蠵
    -1.59
    廰
    -1.55
    Seni
    -1.55
    へ向
    -1.55
    POSITIVE LOGITS
     following
    1.63
     of
    1.60
    $
    1.53
    ↵
    1.49
    ",
    1.48
     donde
    1.34
    })$,
    1.31
    释
    1.29
     we
    1.24
     I
    1.23
    Activations Density 0.006%

    No Known Activations