© 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. 78173
    Prev
    Next
    INDEX
    Explanations

    differential amplification and neuropsychological functioning

    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
    bmp
    -0.74
     thirties
    -0.74
     stumbled
    -0.72
    一次
    -0.69
    скет
    -0.69
    ང་
    -0.68
    精灵
    -0.68
    沿
    -0.68
     XIX
    -0.67
     símbolo
    -0.66
    POSITIVE LOGITS
    Ionic
    0.92
    篇文章
    0.85
    ÓS
    0.82
    illeur
    0.82
     compéti
    0.81
    dée
    0.81
     fielder
    0.79
    Fourni
    0.78
    剩下的
    0.77
     angelegt
    0.77
    Activations Density 0.013%

    No Known Activations