© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2120
    Prev
    Next
    INDEX
    Explanations

    language models and training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    稃
    0.48
    áil
    0.43
    णिज्य
    0.43
    চিব
    0.41
    asList
    0.41
     बाती
    0.41
     ماند
    0.41
    屣
    0.40
    ESSMENT
    0.40
    袜
    0.40
    POSITIVE LOGITS
     pretrained
    1.14
     models
    1.05
     trained
    1.02
     GPT
    1.00
     training
    0.99
    模型
    0.96
     model
    0.92
     transformers
    0.91
     OpenAI
    0.91
     architectures
    0.90
    Activations Density 1.398%

    No Known Activations