© 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. 119403
    Prev
    Next
    INDEX
    Explanations

    schema or code definitions

    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
     DPM
    -0.79
     SFP
    -0.75
     rk
    -0.74
     lk
    -0.73
     खेल
    -0.73
    Réalisation
    -0.72
     lx
    -0.70
     frivol
    -0.70
     Hing
    -0.69
     egress
    -0.69
    POSITIVE LOGITS
    anze
    0.72
     Gerry
    0.70
    ットン
    0.69
    returnValue
    0.69
     vị
    0.67
     misma
    0.67
    日在
    0.66
     completos
    0.66
     faut
    0.64
    థ
    0.64
    Activations Density 0.065%

    No Known Activations