© 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. 67294
    Prev
    Next
    INDEX
    Explanations

    and, or, other conjunctions

    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
     
    -1.00
     mortem
    -0.96
     gants
    -0.93
    performs
    -0.91
     pleg
    -0.88
    すごい
    -0.88
    ほんとに
    -0.88
    豚肉
    -0.87
    “,
    -0.86
    “-
    -0.86
    POSITIVE LOGITS
     its
    1.51
     it
    1.17
     other
    1.13
     from
    1.09
     their
    1.07
    čnosti
    0.98
     related
    0.98
    lipids
    0.98
    lblNewLabel
    0.96
     tỏi
    0.96
    Activations Density 0.135%

    No Known Activations