© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76616
    Prev
    Next
    INDEX
    Explanations

    command line executions

    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
    idences
    -0.83
    lev
    -0.82
    msgs
    -0.79
     needing
    -0.78
    amethasone
    -0.75
     invit
    -0.75
     특
    -0.75
    mr
    -0.73
    datetime
    -0.73
    ばら
    -0.72
    POSITIVE LOGITS
    strze
    0.86
     soldado
    0.86
    goblin
    0.84
     bőr
    0.84
     hossz
    0.84
     enemigo
    0.84
    🚨
    0.82
     červená
    0.81
    experiences
    0.80
    есть
    0.79
    Activations Density 0.007%

    No Known Activations