© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117776
    Prev
    Next
    INDEX
    Explanations

    take a decision

    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
     неда
    -0.73
    -//
    -0.73
    enei
    -0.71
     musica
    -0.71
    Сти
    -0.70
    ENDAR
    -0.70
    activity
    -0.69
     kwenye
    -0.69
     Resource
    -0.69
     географи
    -0.68
    POSITIVE LOGITS
     decisions
    1.18
     decision
    1.13
     advantage
    1.11
     решение
    1.05
     gefangen
    1.02
     possession
    1.01
     Abschied
    0.96
     Abstand
    0.96
     afstand
    0.93
    otations
    0.87
    Activations Density 0.015%

    No Known Activations