© 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. 80805
    Prev
    Next
    INDEX
    Explanations

    indexPath in code

    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
    龃
    -2.78
    
    -2.72
    𞤢
    -2.72
    蟶
    -2.64
    鼍
    -2.64
    衚
    -2.58
    ڧ
    -2.53
    耵
    -2.45
    ⼥
    -2.44
    螃
    -2.42
    POSITIVE LOGITS
     Then
    3.31
    at
    2.31
     On
    2.28
     Also
    2.25
     '
    2.11
    (
    2.09
     Obviously
    2.08
    t
    2.08
     Currently
    2.06
     Presumably
    2.06
    Activations Density 0.001%

    No Known Activations