© 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. 22-GEMMASCOPE-RES-131K
    7. 11212
    Prev
    Next
    INDEX
    Explanations

    object creation and initialization

    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
    preneur
    -1.21
     alcune
    -1.16
    preneurs
    -1.15
    7
    -1.12
    umers
    -1.10
    8
    -1.09
    2
    -1.05
    5
    -1.04
     некото
    -1.02
     idéia
    -1.02
    POSITIVE LOGITS
     ſou
    1.32
     porcelana
    1.22
     barcel
    1.21
     manteau
    1.19
    еру
    1.19
    sumber
    1.17
     """",
    1.16
    唿
    1.16
     pantalon
    1.15
    大全
    1.14
    Activations Density 0.007%

    No Known Activations