© 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. 65476
    Prev
    Next
    INDEX
    Explanations

    prefix questions with Q:

    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
     観光
    -1.15
    mıştır
    -1.05
     oração
    -1.05
     misericordia
    -1.05
     perhaps
    -1.04
    getRepository
    -1.03
    assertIn
    -1.03
     for
    -1.03
     both
    -1.02
     might
    -1.02
    POSITIVE LOGITS
     reaff
    1.08
     минера
    1.08
     poign
    1.04
     laug
    1.03
     tặng
    1.03
     romanti
    1.02
    |')
    1.01
     envía
    1.01
    новь
    0.99
    辍
    0.99
    Activations Density 0.010%

    No Known Activations