© 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. 70985
    Prev
    Next
    INDEX
    Explanations

    coordinates and graphical elements

    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
     that
    -1.05
    だよね
    -0.99
     Moskau
    -0.93
     hanggang
    -0.92
     odp
    -0.91
     which
    -0.91
     kapag
    -0.90
     would
    -0.87
     sampel
    -0.85
    DEPTH
    -0.85
    POSITIVE LOGITS
     vorigen
    1.01
    éia
    0.98
    ▢
    0.96
     dritten
    0.96
    色々な
    0.93
     mittleren
    0.92
     ─
    0.90
    still
    0.90
    最初は
    0.87
    Ultima
    0.86
    Activations Density 0.007%

    No Known Activations