© 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. 10-GEMMASCOPE-RES-131K
    7. 90772
    Prev
    Next
    INDEX
    Explanations

    torture and interrogation

    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_10/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
     <
    -1.30
     condado
    -1.28
     that
    -1.25
     its
    -1.16
    了口气
    -1.11
     grà
    -1.10
    自ら
    -1.05
    !
    -1.03
     Unve
    -1.02
     '
    -1.01
    POSITIVE LOGITS
    Then
    1.43
     cedera
    1.41
    These
    1.41
    ()"
    1.28
     Sekarang
    1.27
    。”
    1.27
    苙
    1.24
     каких
    1.22
     pièce
    1.21
     используются
    1.20
    Activations Density 0.024%

    No Known Activations