© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87227
    Prev
    Next
    INDEX
    Explanations

    creating user identifiers

    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
    釉
    -0.75
    śl
    -0.75
    sterreich
    -0.73
    楂
    -0.73
    South
    -0.68
     calculated
    -0.68
    venes
    -0.68
    ේ
    -0.68
    booted
    -0.67
    €
    -0.67
    POSITIVE LOGITS
     nickname
    1.93
     nicknames
    1.61
     nick
    1.59
     name
    1.44
     username
    1.42
    nickname
    1.35
    Nickname
    1.27
    NickName
    1.17
     Nick
    1.15
    姓名
    1.14
    Activations Density 0.014%

    No Known Activations