© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129741
    Prev
    Next
    INDEX
    Explanations

    mathematical blackboard bold symbols

    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
    を
    -1.58
     "
    -1.53
    が
    -1.27
    などが
    -1.25
    ining
    -1.22
    紧接着
    -1.20
    !!!!!!!
    -1.18
     messen
    -1.16
     !!!!
    -1.15
    が上が
    -1.14
    POSITIVE LOGITS
    During
    1.50
    encre
    1.48
     ciertamente
    1.34
    Despite
    1.33
    Throughout
    1.27
    Several
    1.27
     During
    1.25
     publiek
    1.24
     moeili
    1.21
     nødvendig
    1.21
    Activations Density 0.018%

    No Known Activations