© 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. 27510
    Prev
    Next
    INDEX
    Explanations

    as much as possible

    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
    träge
    -1.23
    我了
    -1.20
     mondiale
    -1.20
     富士
    -1.12
    などが
    -1.12
     ciment
    -1.11
     inverno
    -1.10
     sahiptir
    -1.08
     preparo
    -1.08
    了我
    -1.08
    POSITIVE LOGITS
     cât
    1.23
     Whatever
    1.21
    ↵↵
    1.15
     possible
    1.15
    尽可能
    1.11
     as
    1.09
     максимально
    1.06
    ↵↵↵↵
    1.06
     quam
    1.05
    できるだけ
    1.02
    Activations Density 0.020%

    No Known Activations