© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63321
    Prev
    Next
    INDEX
    Explanations

    creation and completion

    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
     mobilité
    -1.33
     récente
    -1.32
     réforme
    -1.31
    化する
    -1.24
     okru
    -1.23
    の時に
    -1.20
    integrating
    -1.19
     cérémonie
    -1.18
    っていましたが
    -1.16
     мужская
    -1.14
    POSITIVE LOGITS
     creation
    3.83
     removal
    2.67
     introduction
    2.63
     establishment
    2.63
     completion
    2.59
    creation
    2.58
     issuance
    2.50
     implementation
    2.45
     formation
    2.42
     adoption
    2.33
    Activations Density 0.604%

    No Known Activations