© 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. 1594
    Prev
    Next
    INDEX
    Explanations

    come and respond

    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
    嘚
    -1.46
     of
    -1.42
     problemu
    -1.34
     funcionam
    -1.34
     tuvimos
    -1.33
     nhưng
    -1.31
    鯵
    -1.30
     troisième
    -1.28
     verschied
    -1.26
     fueran
    -1.23
    POSITIVE LOGITS
     during
    1.21
     for
    1.19
     frites
    1.11
    ارم
    1.09
    dicht
    1.08
     the
    1.07
     just
    1.06
     There
    1.04
     when
    1.03
     chrétien
    1.03
    Activations Density 0.039%

    No Known Activations