© 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. 22-GEMMASCOPE-RES-131K
    7. 128895
    Prev
    Next
    INDEX
    Explanations

    references to past articles or posts

    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
     After
    -0.98
    Arri
    -0.91
    ↵↵↵
    -0.88
     key
    -0.87
     start
    -0.85
     make
    -0.82
     such
    -0.82
     after
    -0.82
     St
    -0.82
     also
    -0.82
    POSITIVE LOGITS
     previous
    1.38
     blog
    1.31
     предыду
    1.30
    previous
    1.25
     precedenti
    1.23
    ticolo
    1.22
     précédent
    1.22
     last
    1.21
     earlier
    1.17
    previously
    1.14
    Activations Density 0.189%

    No Known Activations