© 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. 72091
    Prev
    Next
    INDEX
    Explanations

    nullable or null checks

    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
     plezier
    -0.97
    Inhoud
    -0.96
     生産
    -0.95
    ふと
    -0.94
     conspicuously
    -0.90
     astonished
    -0.89
    ủa
    -0.88
    時点で
    -0.88
     cardiovas
    -0.87
     thậm
    -0.86
    POSITIVE LOGITS
    Ḥ
    0.96
    灘
    0.91
     дирек
    0.91
       
    0.90
     extremism
    0.89
    '])){
    0.88
    вропей
    0.88
    msgSender
    0.87
    glUniform
    0.86
     ६
    0.85
    Activations Density 0.001%

    No Known Activations