© 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. 34778
    Prev
    Next
    INDEX
    Explanations

    calling code constructs

    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
     ilg
    -1.23
    Características
    -1.14
     For
    -1.14
    Estás
    -1.14
     Kategor
    -1.11
     Så
    -1.11
     tiap
    -1.10
    produzione
    -1.09
    Cómo
    -1.08
    鎂
    -1.08
    POSITIVE LOGITS
    وضوع
    1.38
     effectuer
    1.33
     efectuar
    1.30
    癭
    1.23
     считает
    1.23
     fantastic
    1.18
     wonderful
    1.17
    釹
    1.16
     spectacular
    1.16
     constituyen
    1.16
    Activations Density 0.001%

    No Known Activations