© 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. 128213
    Prev
    Next
    INDEX
    Explanations

    related art and previous

    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
     vilken
    -0.77
    莘
    -0.77
     clima
    -0.77
     okolo
    -0.77
    隨著
    -0.74
    čius
    -0.73
     unthinkable
    -0.73
    パンマン
    -0.73
    SEGUIR
    -0.72
     airtight
    -0.72
    POSITIVE LOGITS
     previous
    3.27
    previous
    2.53
    Previous
    2.47
     existing
    2.42
     Previous
    2.19
     previously
    2.17
     предыду
    2.16
    existing
    2.03
    PREVIOUS
    1.89
     precedenti
    1.83
    Activations Density 0.226%

    No Known Activations