© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65356
    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_34/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
     ceket
    -1.20
     concorda
    -1.20
     conosco
    -1.18
     comunica
    -1.17
     favorece
    -1.15
     conozco
    -1.12
    Демографія
    -1.09
     adoro
    -1.09
     custa
    -1.08
     mantém
    -1.08
    POSITIVE LOGITS
     as
    6.38
     möglichst
    3.66
    尽可能
    3.38
     максимально
    3.09
    できるだけ
    2.56
    なるべく
    2.34
    尽量
    2.30
     максима
    2.23
     asap
    2.17
     maximum
    2.13
    Activations Density 0.243%

    No Known Activations