© 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. 34-GEMMASCOPE-RES-131K
    7. 84604
    Prev
    Next
    INDEX
    Explanations

    user identifying user input

    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_34/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
    cmt
    -0.77
    delse
    -0.74
     hidro
    -0.71
    DEPART
    -0.71
     Depart
    -0.69
    Atta
    -0.69
    col
    -0.68
    ometr
    -0.68
     subnet
    -0.68
     salade
    -0.68
    POSITIVE LOGITS
     user
    1.55
     users
    1.36
     User
    1.36
     copy
    1.23
     Users
    1.22
    用户
    1.13
     USER
    1.09
    User
    1.08
    user
    1.08
    ユーザー
    1.05
    Activations Density 0.060%

    No Known Activations