© 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. 103009
    Prev
    Next
    INDEX
    Explanations

    combat actions and locations

    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
    nachweise
    -1.14
    uscht
    -1.09
    AddField
    -1.02
     Vitamina
    -1.00
     både
    -0.97
     plong
    -0.96
    ORIES
    -0.94
     entrevist
    -0.94
     almacen
    -0.93
     scènes
    -0.93
    POSITIVE LOGITS
     reposition
    1.33
     engage
    1.19
     while
    1.19
     near
    1.15
     agro
    1.12
     focused
    1.10
     engaged
    1.07
     ranged
    1.07
     close
    1.05
     positioned
    1.05
    Activations Density 0.014%

    No Known Activations