© 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. 73904
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

    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
     souverain
    -0.88
     esthétique
    -0.85
    evident
    -0.84
     Cola
    -0.83
    primarily
    -0.82
     decy
    -0.82
     mlu
    -0.81
    opot
    -0.81
    cadora
    -0.81
    requestData
    -0.81
    POSITIVE LOGITS
     būt
    0.94
     arresting
    0.85
     comunale
    0.81
     adatto
    0.79
    getPort
    0.79
    skine
    0.77
     approx
    0.76
     XXXVI
    0.76
    łow
    0.75
     интен
    0.75
    Activations Density 0.023%

    No Known Activations