© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35275
    Prev
    Next
    INDEX
    Explanations

    numbers and business strategies

    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
     ویتامین
    -1.51
     别墅
    -1.38
     pekan
    -1.36
    alians
    -1.35
    Terug
    -1.34
     specchio
    -1.34
    อร่อย
    -1.33
    Aantal
    -1.33
    ſtra
    -1.32
     nemico
    -1.31
    POSITIVE LOGITS
     your
    2.36
     you
    2.03
    :
    1.60
     
    1.48
    1.38
     +
    1.37
    $
    1.36
    ७
    1.34
    ...
    1.34
    ’
    1.31
    Activations Density 0.039%
    No Known Activations