© 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. 80745
    Prev
    Next
    INDEX
    Explanations

    hexadecimal hashes and codes

    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
    caucasian
    -1.70
     to
    -1.65
    kenal
    -1.63
    daun
    -1.63
    collier
    -1.59
    seag
    -1.59
    chalet
    -1.56
     How
    -1.56
     during
    -1.55
     by
    -1.55
    POSITIVE LOGITS
     barnet
    1.72
     bourg
    1.69
     kazak
    1.69
    ícias
    1.63
     vasi
    1.61
     morti
    1.58
     autres
    1.57
     steen
    1.57
    fillment
    1.55
     paloma
    1.54
    Activations Density 0.030%

    No Known Activations