© 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. 22-GEMMASCOPE-RES-131K
    7. 98485
    Prev
    Next
    INDEX
    Explanations

    focus, concentration, attention

    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_22/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
    hésitez
    -1.23
    kennen
    -1.11
     vivere
    -1.10
    桫
    -1.10
     vedere
    -1.10
    骞
    -1.08
     birbir
    -1.08
     servire
    -1.08
    サキ
    -1.05
    lijf
    -1.05
    POSITIVE LOGITS
     focus
    1.52
     focused
    1.39
     required
    1.30
     attention
    1.22
     concentration
    1.20
    Focus
    1.19
     intently
    1.16
     concentrate
    1.14
     only
    1.13
     during
    1.10
    Activations Density 0.017%

    No Known Activations