© 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. 22-GEMMASCOPE-RES-131K
    7. 72434
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     it
    -1.11
    いかない
    -0.84
    óbal
    -0.81
    sslich
    -0.81
     misma
    -0.81
     which
    -0.80
     diferentes
    -0.79
     xícara
    -0.79
     Alleg
    -0.77
    経歴
    -0.77
    POSITIVE LOGITS
    genero
    0.96
    핌
    0.91
     indoc
    0.87
    zach
    0.86
     disconnecting
    0.86
    ostructures
    0.85
    їна
    0.85
    onAttach
    0.81
    koma
    0.81
    ärna
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.