© 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. 65429
    Prev
    Next
    INDEX
    Explanations

    technical specifications or dimensions

    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
    僦
    -1.05
    をします
    -1.02
    えっ
    -1.00
    を行います
    -0.97
    的時間
    -0.96
    的过程中
    -0.95
     haberse
    -0.92
     suspensão
    -0.92
     mesmo
    -0.91
    서울
    -0.91
    POSITIVE LOGITS
     with
    1.75
     of
    1.42
     in
    1.24
     and
    1.23
     for
    1.23
     on
    1.18
     वाली
    1.17
     वाले
    1.13
     version
    1.12
     versions
    1.10
    Activations Density 0.272%

    No Known Activations