© 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. 91061
    Prev
    Next
    INDEX
    Explanations

    strategic, therapeutic, real, development

    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
    الصفحه
    -0.84
     matrícula
    -0.81
    шной
    -0.79
    Clarke
    -0.77
     recherches
    -0.76
    一系列
    -0.75
    ditionally
    -0.74
    PostId
    -0.73
    DM
    -0.73
    してない
    -0.73
    POSITIVE LOGITS
     transverse
    1.19
     Transverse
    1.06
     actors
    0.95
     actor
    0.94
    }}^{(
    0.91
     aktor
    0.90
    }^{(
    0.90
     França
    0.88
    acteur
    0.87
    Actor
    0.85
    Activations Density 0.055%

    No Known Activations