© 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. 34-GEMMASCOPE-RES-131K
    7. 57385
    Prev
    Next
    INDEX
    Explanations

    surnames

    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
     its
    -1.36
    buatan
    -1.15
    chemise
    -1.02
     vantaggio
    -1.01
     itself
    -1.01
     либо
    -1.00
    importation
    -1.00
     either
    -1.00
    ฌ
    -0.98
     inoltre
    -0.96
    POSITIVE LOGITS
    antism
    1.27
     Jr
    1.27
     italien
    1.22
    loggen
    1.13
     jr
    1.09
     آوری
    1.08
     (†
    1.05
    Украина
    1.05
    hooting
    1.05
     née
    1.02
    Activations Density 0.094%

    No Known Activations