© 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. 130580
    Prev
    Next
    INDEX
    Explanations

    .extends, .nic, .png

    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
     to
    -2.09
     bawat
    -1.42
     and
    -1.40
     also
    -1.39
     followed
    -1.34
    nasional
    -1.30
     with
    -1.27
    erà
    -1.27
    🖤
    -1.23
    Ⓡ
    -1.23
    POSITIVE LOGITS
     maravill
    1.63
    卧槽
    1.47
     lhes
    1.45
     SOMETHING
    1.38
     refuer
    1.38
     increíbles
    1.30
     scheinen
    1.30
    犼
    1.29
    Grazie
    1.28
     llamaba
    1.28
    Activations Density 0.084%

    No Known Activations