© 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. 10-GEMMASCOPE-RES-131K
    7. 99771
    Prev
    Next
    INDEX
    Explanations

    competition and games

    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_10/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
     but
    -1.59
     as
    -1.45
     have
    -1.36
     after
    -1.25
     although
    -1.25
     despite
    -1.23
    avaient
    -1.20
    五百
    -1.20
     who
    -1.17
     didn
    -1.16
    POSITIVE LOGITS
     Infir
    1.30
     Reserva
    1.30
     cadeaux
    1.27
     apresentado
    1.27
    在一个
    1.26
    ﹣
    1.25
    ーーーー
    1.24
     pakai
    1.24
    iç
    1.23
    pág
    1.22
    Activations Density 0.055%

    No Known Activations