© 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. 72440
    Prev
    Next
    INDEX
    Explanations

    names or introductions

    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
    ⻬
    -1.16
    属于
    -1.09
    gruss
    -1.03
    hijab
    -1.03
    katy
    -1.02
     isActive
    -1.01
    本当に
    -1.00
    archiwizowane
    -0.98
    以及
    -0.98
    とにかく
    -0.98
    POSITIVE LOGITS
     we
    1.28
     now
    1.22
     they
    1.02
     should
    1.01
    androidx
    1.00
     more
    0.98
     lepiej
    0.94
     it
    0.92
     could
    0.91
     avoiding
    0.90
    Activations Density 0.013%

    No Known Activations