© 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. 109215
    Prev
    Next
    INDEX
    Explanations

    we propose

    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
    ἃ
    -1.01
    🆗
    -0.98
    勤務
    -0.96
    #%%
    -0.95
     tacón
    -0.94
    hlás
    -0.94
     silla
    -0.94
    ført
    -0.94
     menggunakan
    -0.93
     refroid
    -0.93
    POSITIVE LOGITS
     our
    1.67
     we
    1.60
     since
    1.50
     instead
    1.45
     unlike
    1.44
     We
    1.38
     Instead
    1.34
     Our
    1.31
     inspired
    1.29
     to
    1.27
    Activations Density 0.056%

    No Known Activations