© 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. 27213
    Prev
    Next
    INDEX
    Explanations

    enduring relevance today

    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
     but
    -1.22
     then
    -1.12
     sientes
    -1.10
     maggiore
    -1.05
    конец
    -1.05
     empiezan
    -1.03
     fuimos
    -1.02
    pozorn
    -1.01
     раньше
    -1.00
    امکان
    -1.00
    POSITIVE LOGITS
     still
    2.28
     vẫn
    1.69
     tetap
    1.66
     stále
    1.52
     unchanged
    1.45
    still
    1.43
     remain
    1.39
     despite
    1.37
    仍
    1.36
    依旧
    1.35
    Activations Density 0.039%

    No Known Activations