© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129798
    Prev
    Next
    INDEX
    Explanations

    quantities and variations

    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_22/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
    tiéndose
    -1.22
    tiendo
    -1.13
     نداره
    -1.12
    而是
    -1.10
    weren
    -1.09
     teve
    -1.09
    的原因
    -1.07
    聼
    -1.06
     razones
    -1.06
    很多
    -1.05
    POSITIVE LOGITS
     each
    2.13
     various
    2.02
     verschiedenen
    1.66
     how
    1.56
     berbagai
    1.54
     different
    1.50
     مختلف
    1.48
     olika
    1.45
     your
    1.41
     if
    1.40
    Activations Density 0.060%

    No Known Activations