© 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. 15893
    Prev
    Next
    INDEX
    Explanations

    closing markup tags

    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
     imposter
    -1.04
     bodied
    -1.00
     inev
    -1.00
     catast
    -1.00
     ranting
    -0.98
     brachten
    -0.97
     immor
    -0.96
    wyczaj
    -0.96
     slashes
    -0.96
     congr
    -0.94
    POSITIVE LOGITS
     no
    1.25
     on
    1.21
     in
    1.09
     will
    1.01
    </h1>
    1.00
     sein
    0.97
    },
    0.96
    StartIndex
    0.93
     start
    0.92
     estaba
    0.91
    Activations Density 0.027%

    No Known Activations