© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33327
    Prev
    Next
    INDEX
    Explanations

    disabled state

    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
     necesar
    -1.17
    جابة
    -1.11
    geth
    -1.07
    ))}
    -1.05
    ♭
    -1.04
     obat
    -1.02
     nosi
    -1.01
    gone
    -1.01
    commodation
    -1.00
    pherds
    -0.99
    POSITIVE LOGITS
    Some
    1.20
    bandeja
    1.09
     disabled
    1.09
    sə
    0.98
     ПОД
    0.97
    Several
    0.96
    씀
    0.96
    yecek
    0.95
     boxeo
    0.94
    There
    0.94
    Activations Density 0.007%

    No Known Activations