© 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. 22-GEMMASCOPE-RES-131K
    7. 15256
    Prev
    Next
    INDEX
    Explanations

    listing other items

    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
     and
    -2.09
     nabíz
    -1.15
    komplet
    -1.13
     hört
    -1.09
     obchod
    -1.09
    性和
    -1.09
    劾
    -1.08
    tığı
    -1.07
    カナダ
    -1.02
     koment
    -1.02
    POSITIVE LOGITS
     that
    1.77
     of
    1.74
     lainnya
    1.62
     such
    1.52
     you
    1.46
     others
    1.41
     other
    1.41
     we
    1.34
     which
    1.28
     других
    1.20
    Activations Density 0.029%

    No Known Activations