© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67474
    Prev
    Next
    INDEX
    Explanations

    C++ metaprogramming, templates, and iterators

    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
     was
    -1.52
    |+\
    -1.48
     letzt
    -1.41
     mogą
    -1.39
    AGRAM
    -1.37
     Obituary
    -1.37
    ￨
    -1.35
    籏
    -1.35
    +)$
    -1.34
     スカイ
    -1.32
    POSITIVE LOGITS
    ,
    1.34
     I
    1.31
    .
    1.24
    Etimo
    1.23
    Paket
    1.22
    atleta
    1.20
    等は
    1.20
     or
    1.20
     gekauft
    1.15
    Chromosome
    1.15
    Activations Density 0.118%

    No Known Activations