© 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. 60926
    Prev
    Next
    INDEX
    Explanations

    andrew followed by a surname

    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
    and
    -3.31
    to
    -3.20
    on
    -3.16
     But
    -2.92
    but
    -2.80
    秾
    -2.44
     largely
    -2.39
     conspired
    -2.38
    也很
    -2.36
     筒
    -2.33
    POSITIVE LOGITS
    菝
    2.80
    芣
    2.64
     behulp
    2.53
    ᠁
    2.47
    ꯵
    2.44
    AdvEx
    2.42
    罽
    2.39
    唿
    2.36
    哢
    2.33
    劊
    2.27
    Activations Density 0.003%

    No Known Activations