© 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. 93181
    Prev
    Next
    INDEX
    Explanations

    detention and military tribunals

    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
     invita
    -0.77
    는데
    -0.76
     solicita
    -0.75
     stationnement
    -0.75
    gante
    -0.74
    𝐍
    -0.74
     verifica
    -0.73
     catalytic
    -0.73
     >=
    -0.73
    }$.
    -0.72
    POSITIVE LOGITS
     detaine
    1.13
     Gu
    1.02
     habeas
    0.98
     detainees
    0.96
     detención
    0.91
     DOD
    0.90
     Pentagon
    0.88
    prison
    0.88
     Gefang
    0.86
     prisoner
    0.85
    Activations Density 0.017%

    No Known Activations