© 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. 30489
    Prev
    Next
    INDEX
    Explanations

    bankruptcy confirmation Chapter

    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
     boomer
    -0.96
     declar
    -0.90
     tunne
    -0.82
     Indones
    -0.81
     Lambeth
    -0.78
     PRODUC
    -0.78
     Nassau
    -0.77
    vernote
    -0.76
    TOBER
    -0.76
     FLAC
    -0.76
    POSITIVE LOGITS
     confirmation
    1.00
     confirmed
    0.97
     confirmar
    0.95
     conferma
    0.84
     confirmado
    0.84
     confirmó
    0.81
    Confirmation
    0.80
     confirming
    0.78
    tické
    0.77
     United
    0.76
    Activations Density 0.062%

    No Known Activations