© 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. 69072
    Prev
    Next
    INDEX
    Explanations

    names of companies, denominations, or books

    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
     bessere
    -1.36
    grees
    -1.34
     verschied
    -1.32
    诶
    -1.25
    変わらない
    -1.25
    
    -1.20
    別に
    -1.20
    Люби
    -1.20
    更好地
    -1.19
    dication
    -1.18
    POSITIVE LOGITS
     will
    1.71
     and
    1.48
     as
    1.28
     is
    1.27
    mø
    1.21
    一二
    1.19
    fato
    1.19
    packageName
    1.17
     машину
    1.17
    CAPTION
    1.16
    Activations Density 0.149%

    No Known Activations