© 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. 474
    Prev
    Next
    INDEX
    Explanations

    magnification and enlargement

    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
    ResourceBundle
    -0.75
    sik
    -0.73
    rischen
    -0.71
    ভ
    -0.70
    ukar
    -0.69
    kg
    -0.69
     RR
    -0.67
    ISE
    -0.67
     komplet
    -0.66
    ArrayAdapter
    -0.66
    POSITIVE LOGITS
     magnified
    4.13
     magnification
    4.13
     magnify
    3.64
     enlarged
    3.42
     magnifying
    3.36
    放大
    3.25
     Magn
    3.14
    magn
    3.13
     enlargement
    3.13
     enlarge
    3.09
    Activations Density 0.070%

    No Known Activations