© 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. 22-GEMMASCOPE-RES-131K
    4. 79781
    Prev
    Next
    INDEX
    Explanations

    specific numbers and names

    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
     workday
    -1.08
     リング
    -1.08
     např
    -1.07
     nejen
    -1.04
     ヘア
    -1.02
     було
    -1.02
    Mediabestanden
    -1.00
    怦
    -1.00
    多くの
    -0.99
    brale
    -0.98
    POSITIVE LOGITS
     recently
    1.20
     неизвест
    1.11
     specific
    1.10
    ,「
    1.09
     probably
    1.05
    说法
    1.05
    recently
    1.03
    ONAUT
    1.03
     Tyskland
    1.02
     }}$
    1.01
    Activations Density 0.043%

    No Known Activations