© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90656
    Prev
    Next
    INDEX
    Explanations

    official gazette and legal notices

    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
     vergeben
    -0.85
    reet
    -0.84
    adox
    -0.76
    íč
    -0.72
    🔂
    -0.71
    聞こ
    -0.71
    jectures
    -0.70
    Preface
    -0.69
    шкой
    -0.69
     płasz
    -0.69
    POSITIVE LOGITS
     gaz
    3.61
     Gazette
    3.19
     Gaz
    2.58
    Gaz
    2.39
    Gazette
    2.36
    gaz
    2.28
    gazette
    2.23
     GAZ
    2.11
     Gazz
    1.68
     gaze
    1.49
    Activations Density 0.035%

    No Known Activations