© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15970
    Prev
    Next
    INDEX
    Explanations

    product launches and announcements

    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
     my
    -1.63
     children
    -1.51
    ⼈
    -1.35
     algunos
    -1.34
     quando
    -1.34
     angry
    -1.29
     some
    -1.27
     sogar
    -1.25
     muchos
    -1.25
     cases
    -1.25
    POSITIVE LOGITS
     surgiu
    1.47
     perdeu
    1.38
     fizeram
    1.38
     atualizar
    1.37
    湳
    1.32
     servem
    1.30
     morreu
    1.30
     mudou
    1.28
     esteve
    1.25
     passaram
    1.24
    Activations Density 0.039%

    No Known Activations