© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1445
    Prev
    Next
    INDEX
    Explanations

    resistance and resistance members

    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
     brimming
    -0.77
     postnatal
    -0.75
     entourage
    -0.75
     भाषा
    -0.74
    adero
    -0.74
     eliminare
    -0.73
    tingham
    -0.73
     extradition
    -0.72
     mercenaries
    -0.72
    ApiRequest
    -0.71
    POSITIVE LOGITS
     resistance
    1.24
    resistance
    1.07
     Resistance
    1.05
    agents
    1.02
     underground
    1.02
     agent
    0.99
    Resistance
    0.98
     sabotage
    0.95
     Widerstand
    0.94
     agents
    0.94
    Activations Density 0.038%

    No Known Activations