© 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. 70769
    Prev
    Next
    INDEX
    Explanations

    technical and descriptive phrases

    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
     for
    -1.59
     their
    -1.42
     first
    -1.31
    1
    -1.21
     all
    -1.21
     on
    -1.20
     they
    -1.16
     because
    -1.16
     make
    -1.14
     begin
    -1.14
    POSITIVE LOGITS
    极为
    1.23
    ܆
    1.16
    POUR
    1.16
    櫪
    1.13
     Forming
    1.13
    avons
    1.13
    coloriage
    1.13
     maniere
    1.13
     Vomiting
    1.13
     famed
    1.13
    Activations Density 0.000%

    No Known Activations