© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58984
    Prev
    Next
    INDEX
    Explanations

    company names and their products/associates

    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
    h
    -3.28
     '
    -2.94
    '
    -2.73
    ar
    -2.66
     Choosing
    -2.64
    t
    -2.63
    u
    -2.50
    o
    -2.48
    )
    -2.45
     OF
    -2.44
    POSITIVE LOGITS
    敺
    3.13
    驁
    2.92
     anhänger
    2.64
    麃
    2.59
    鋨
    2.41
    ﹶ
    2.36
    銪
    2.31
    拶
    2.31
     hiperten
    2.28
    グルト
    2.27
    Activations Density 0.002%

    No Known Activations