© 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. 10-GEMMASCOPE-RES-131K
    7. 59797
    Prev
    Next
    INDEX
    Explanations

    names starting with Ger

    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_10/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
    籥
    -3.05
    鋱
    -2.95
    ଝ
    -2.89
    豋
    -2.83
    𓋼
    -2.81
    ꯸
    -2.80
    未完
    -2.75
    孥
    -2.69
     indiví
    -2.67
    ズニー
    -2.64
    POSITIVE LOGITS
    ’
    5.03
    0
    4.88
    2
    3.95
    1
    3.64
    9
    3.53
    3
    3.50
    ,”
    3.33
    7
    3.11
    ，
    3.06
    6
    2.88
    Activations Density 0.004%

    No Known Activations