© 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. 119413
    Prev
    Next
    INDEX
    Explanations

    character ranks and titles

    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
     cantante
    -0.84
    籟
    -0.84
    Zdra
    -0.82
    พี่
    -0.80
    показа
    -0.78
    Schwer
    -0.78
     પા
    -0.77
     früheren
    -0.75
     сахара
    -0.75
    leistungs
    -0.74
    POSITIVE LOGITS
     Agent
    1.29
     Major
    1.18
    Major
    1.13
    Lt
    1.02
    Agent
    1.02
     Lt
    1.02
     Lieutenant
    1.02
     Captain
    1.02
     Chief
    0.98
    Captain
    0.94
    Activations Density 0.025%

    No Known Activations