© 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. 65366
    Prev
    Next
    INDEX
    Explanations

    headers followed by titles

    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
     sei
    -0.98
     schon
    -0.94
    传统的
    -0.93
    欧式
    -0.93
     있으며
    -0.92
    ględ
    -0.90
     Naomi
    -0.90
    یں
    -0.89
    zkod
    -0.89
     falso
    -0.88
    POSITIVE LOGITS
     ofrecen
    1.00
    Ď
    0.94
     découver
    0.94
     piensan
    0.92
     nordrhein
    0.91
     presentarse
    0.91
     vendus
    0.91
     denkt
    0.90
     connaître
    0.89
     находятся
    0.88
    Activations Density 0.024%

    No Known Activations