© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59923
    Prev
    Next
    INDEX
    Explanations

    factors influencing outcomes

    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
     several
    -1.50
    paravant
    -1.50
     numerous
    -1.37
    𐍆
    -1.36
    专注
    -1.34
    ᥬ
    -1.32
    unno
    -1.31
    灕
    -1.30
    omorph
    -1.28
    クルマ
    -1.28
    POSITIVE LOGITS
     such
    1.65
     and
    1.55
     including
    1.46
     or
    1.36
     県
    1.29
     which
    1.28
     Paesi
    1.24
    或
    1.23
     новых
    1.23
     fijne
    1.23
    Activations Density 0.109%

    No Known Activations