© 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. 22-GEMMASCOPE-RES-131K
    7. 68789
    Prev
    Next
    INDEX
    Explanations

    lambda `=>` expressions

    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
    </b>
    -1.11
    Promises
    -1.04
     those
    -1.03
     used
    -1.00
     two
    -1.00
     only
    -0.98
    </strong>
    -0.94
     before
    -0.93
    fowl
    -0.91
     fusca
    -0.91
    POSITIVE LOGITS
    着自己的
    1.26
     miró
    1.20
     its
    1.14
     bricolaje
    1.12
    着脸
    1.10
    的には
    1.09
     subió
    1.09
     agujeros
    1.08
     wiedzieć
    1.07
     seleccionamos
    1.06
    Activations Density 0.007%

    No Known Activations