© 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. 22-GEMMASCOPE-RES-131K
    7. 38568
    Prev
    Next
    INDEX
    Explanations

    URLs and git repositories

    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_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
     these
    -1.09
     ușor
    -1.08
     our
    -1.07
    不允许
    -1.01
     all
    -1.00
     Klavier
    -0.96
     Our
    -0.94
     naszego
    -0.93
    wały
    -0.93
     wahl
    -0.91
    POSITIVE LOGITS
     from
    1.15
    podob
    1.00
     lequel
    1.00
     pleases
    0.98
     설
    0.98
    antenimiento
    0.96
    Carex
    0.96
     JMenuItem
    0.94
     också
    0.94
     écouter
    0.94
    Activations Density 0.028%

    No Known Activations