© 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. 34-GEMMASCOPE-RES-131K
    7. 83266
    Prev
    Next
    INDEX
    Explanations

    words starting with Miz, Mez, Metz, Mhz

    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_34/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
    dificio
    -0.69
     createSlice
    -0.68
     rodz
    -0.68
     stillness
    -0.67
    ticularly
    -0.67
     favorable
    -0.66
    Creates
    -0.66
    烩
    -0.66
     Offic
    -0.66
     Continued
    -0.66
    POSITIVE LOGITS
    égias
    0.80
    %</
    0.77
    keyframes
    0.77
    MOON
    0.75
    душка
    0.75
     Miz
    0.72
    inazione
    0.72
    fit
    0.72
    TableName
    0.71
     Prospect
    0.71
    Activations Density 0.019%

    No Known Activations