© 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. 22-GEMMASCOPE-RES-131K
    7. 461
    Prev
    Next
    INDEX
    Explanations

    intended or supposed

    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
     Vedi
    -0.90
     depends
    -0.89
     Selanjutnya
    -0.80
    PDT
    -0.80
    Importance
    -0.79
    訣
    -0.79
    ftances
    -0.79
    êncio
    -0.78
    demografi
    -0.78
    enthal
    -0.78
    POSITIVE LOGITS
     intended
    1.70
     originally
    1.63
     initially
    1.55
     merely
    1.46
     expected
    1.36
    intended
    1.29
     Initially
    1.28
     initial
    1.25
    Initially
    1.22
     supposed
    1.20
    Activations Density 0.110%

    No Known Activations