© 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. 79899
    Prev
    Next
    INDEX
    Explanations

    classes, drugs, items, objects

    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
     was
    -1.80
     is
    -1.62
     it
    -1.55
     including
    -1.54
     its
    -1.54
     such
    -1.50
     has
    -1.32
     after
    -1.28
     several
    -1.25
     itself
    -1.20
    POSITIVE LOGITS
     themselves
    2.16
     eivät
    1.70
    themselves
    1.66
     jejich
    1.63
     Their
    1.51
     They
    1.50
     ihnen
    1.47
     ihren
    1.45
     jepang
    1.44
    都不能
    1.44
    Activations Density 0.080%

    No Known Activations