© 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. 70774
    Prev
    Next
    INDEX
    Explanations

    sports team names

    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
     that
    -1.41
     your
    -1.30
    /
    -1.25
     people
    -1.23
     /
    -1.23
     fordern
    -1.20
     freaking
    -1.17
    \
    -1.16
     it
    -1.15
    ふと
    -1.15
    POSITIVE LOGITS
     ponts
    1.35
     ibis
    1.35
     fers
    1.30
     yal
    1.30
    TTTT
    1.24
    llllll
    1.23
     tirs
    1.22
    Mundo
    1.21
    pkins
    1.20
     Ă
    1.20
    Activations Density 0.029%

    No Known Activations