© 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. 49914
    Prev
    Next
    INDEX
    Explanations

    Scott and associated 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_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
     Therefore
    -0.89
     
    -0.83
     Roughly
    -0.82
     
    -0.82
    近年来
    -0.82
    肚子
    -0.81
    uck
    -0.81
     Accordingly
    -0.80
    かわい
    -0.80
    able
    -0.80
    POSITIVE LOGITS
    tish
    1.20
    dale
    1.14
    リコン
    1.06
    rade
    1.05
    󠁴
    1.02
     continúas
    1.00
     այ
    0.98
    pouring
    0.97
     plausible
    0.96
    scot
    0.96
    Activations Density 0.008%

    No Known Activations