© 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. 93971
    Prev
    Next
    INDEX
    Explanations

    position above

    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
    lnk
    -0.79
    Unter
    -0.77
    ู้
    -0.74
    ösungen
    -0.72
    里
    -0.69
    龠
    -0.68
    uxedo
    -0.67
     Unter
    -0.67
    volt
    -0.67
    cette
    -0.67
    POSITIVE LOGITS
     above
    6.53
    above
    5.00
    Above
    4.50
     над
    4.31
     Above
    4.06
     acima
    3.72
     boven
    3.55
     ABOVE
    3.42
     diatas
    2.98
     sopra
    2.92
    Activations Density 0.106%

    No Known Activations