© 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. 35200
    Prev
    Next
    INDEX
    Explanations

    section labels

    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
     広場
    -1.63
     fluide
    -1.59
     inond
    -1.55
     間取り
    -1.52
     estadounid
    -1.48
     rigide
    -1.47
    熜
    -1.47
     levier
    -1.45
     effici
    -1.45
     Resmi
    -1.45
    POSITIVE LOGITS
     to
    1.82
     what
    1.81
     also
    1.67
     How
    1.66
     used
    1.60
     additional
    1.59
     What
    1.59
     Note
    1.54
     about
    1.53
     About
    1.53
    Activations Density 0.018%

    No Known Activations