© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 74926
    Prev
    Next
    INDEX
    Explanations

    code, data, or definitions

    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
     it
    -1.80
     from
    -1.70
     at
    -1.63
     their
    -1.63
     any
    -1.59
     or
    -1.56
     by
    -1.44
     most
    -1.44
     swiftly
    -1.43
     now
    -1.42
    POSITIVE LOGITS
    usually
    1.53
    なども
    1.39
     AMAZING
    1.38
     poë
    1.38
     tyto
    1.35
     새로운
    1.33
     horrid
    1.32
    therefore
    1.32
    amazing
    1.30
     prét
    1.28
    Activations Density 0.006%

    No Known Activations