© 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. 65686
    Prev
    Next
    INDEX
    Explanations

    editing and resource management

    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
     drawing
    -0.85
    Ctl
    -0.76
    慟
    -0.76
    ikuti
    -0.74
     Drawing
    -0.73
    علن
    -0.73
    amigos
    -0.73
     húmedo
    -0.72
    זו
    -0.70
    дву
    -0.70
    POSITIVE LOGITS
     edits
    1.15
     edit
    1.09
     resources
    1.05
    edit
    1.03
    resources
    1.02
     dividers
    1.02
     Edits
    1.02
     editing
    1.01
     manipula
    0.98
    resource
    0.97
    Activations Density 0.014%

    No Known Activations