© 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. 34-GEMMASCOPE-RES-131K
    7. 93818
    Prev
    Next
    INDEX
    Explanations

    special characters, purpose, functions

    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_34/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
    hockey
    -0.90
    救命
    -0.79
    …？
    -0.77
    过来
    -0.76
     bezpeč
    -0.75
    Sådan
    -0.75
    рых
    -0.74
     querem
    -0.72
    カンド
    -0.71
     obtuvo
    -0.71
    POSITIVE LOGITS
    ised
    1.19
     circumstances
    1.17
     Purpose
    1.09
    purpose
    1.09
     purpose
    1.06
    isation
    1.06
     Special
    1.05
    Special
    1.03
    special
    1.02
     Circumstances
    1.02
    Activations Density 0.013%

    No Known Activations