© 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. 84171
    Prev
    Next
    INDEX
    Explanations

    lives up to expectations

    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
     autoridad
    -0.76
    vidla
    -0.75
    ‌آم
    -0.75
     phục
    -0.74
    莎
    -0.73
     trống
    -0.73
    łaści
    -0.72
     klare
    -0.71
    uktion
    -0.70
     ciência
    -0.70
    POSITIVE LOGITS
     up
    2.06
     justify
    1.60
     оправ
    1.57
     upto
    1.56
     justifies
    1.36
     lived
    1.33
    lived
    1.32
    upto
    1.31
     justified
    1.27
     expectations
    1.26
    Activations Density 0.012%

    No Known Activations