© 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. 10-GEMMASCOPE-RES-131K
    7. 60990
    Prev
    Next
    INDEX
    Explanations

    words starting with cor

    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_10/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
    恹
    -2.88
    籥
    -2.81
     ofreci
    -2.81
     obcí
    -2.72
    cím
    -2.70
    姽
    -2.70
    vantaged
    -2.64
    糨
    -2.63
    簠
    -2.59
    ꦫ
    -2.58
    POSITIVE LOGITS
    3
    4.97
    2
    4.94
    7
    4.22
    9
    4.09
    0
    4.09
    1
    3.92
    6
    3.92
    5
    3.72
    an
    3.61
     {
    3.61
    Activations Density 0.004%

    No Known Activations