© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71099
    Prev
    Next
    INDEX
    Explanations

    forming using molds, dies, or stencils

    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
    ְּ
    -1.16
     links
    -1.13
    攔
    -1.13
     lisäksi
    -1.10
    ॉन
    -1.09
    Kanpo
    -1.09
    Link
    -1.09
    odynamics
    -1.08
    links
    -1.06
    Irlande
    -1.06
    POSITIVE LOGITS
     pracę
    1.16
    СЯ
    1.16
    скажите
    1.12
    ဴ
    1.11
    ampang
    1.11
    .''
    1.10
    idro
    1.08
     paradiso
    1.08
     producing
    1.07
     χρησιμοποι
    1.07
    Activations Density 0.078%

    No Known Activations