© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66183
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
     if
    -1.29
     hogyan
    -1.26
     from
    -1.23
     eredeti
    -1.23
     gondol
    -1.12
    pergillus
    -1.11
    الى
    -1.09
    <bos>
    -1.09
     as
    -1.09
     öt
    -1.09
    POSITIVE LOGITS
     !
    1.59
     левый
    1.29
    !
    1.27
     alguno
    1.26
     sostener
    1.24
     gustar
    1.23
    豋
    1.19
     nguyễn
    1.10
    ビックリ
    1.10
     satisfacer
    1.09
    Activations Density 0.010%

    No Known Activations