© 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. 70616
    Prev
    Next
    INDEX
    Explanations

    reporting evidence or trends

    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
     делает
    -1.64
    過ごし
    -1.29
     заниматься
    -1.27
     embarc
    -1.26
     renovar
    -1.26
     никогда
    -1.26
    してました
    -1.25
     realizzazione
    -1.23
     their
    -1.22
     läßt
    -1.22
    POSITIVE LOGITS
     of
    3.78
     to
    3.44
     that
    2.45
     for
    1.53
     by
    1.38
    бище
    1.27
     både
    1.25
    "")
    1.25
     (
    1.23
    ଃ
    1.21
    Activations Density 0.050%

    No Known Activations