© 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. 20515
    Prev
    Next
    INDEX
    Explanations

    URLs, code, numbers, links

    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
     one
    -1.53
     It
    -1.45
     well
    -1.42
     Still
    -1.38
     and
    -1.38
     have
    -1.35
     ,
    -1.32
     an
    -1.30
     just
    -1.29
     enhancing
    -1.29
    POSITIVE LOGITS
     unſ
    1.65
    ครื่อง
    1.59
    糁
    1.59
     mettent
    1.52
    ication
    1.47
    粜
    1.46
    鶫
    1.43
    Ար
    1.40
     ſever
    1.40
     utilisent
    1.36
    Activations Density 0.022%

    No Known Activations