© 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. 27249
    Prev
    Next
    INDEX
    Explanations

    recently + verb

    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
     we
    -2.13
     our
    -2.06
     their
    -1.93
     themselves
    -1.76
     itself
    -1.69
     its
    -1.62
     any
    -1.59
    我們
    -1.59
     you
    -1.58
     what
    -1.57
    POSITIVE LOGITS
    4
    1.60
    //!
    1.56
    7
    1.50
     myself
    1.48
    GRAFÍA
    1.48
    9
    1.45
    8
    1.45
    /***
    1.38
    ++
    1.36
    GRAFIA
    1.34
    Activations Density 0.125%

    No Known Activations