© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4205
    Prev
    Next
    INDEX
    Explanations

    self-supervision on input sequences

    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_262k_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
     heartache
    0.41
    躹
    0.38
    应用程序
    0.37
    马克
    0.36
     irony
    0.35
     فرق
    0.34
     पद्धति
    0.34
    ार्मिक
    0.33
    getSaveLocation
    0.33
    萧
    0.33
    POSITIVE LOGITS
     perturbed
    0.53
     noisy
    0.51
     logits
    0.51
     embeddings
    0.50
     softmax
    0.49
     input
    0.49
     perturbations
    0.46
     posterior
    0.46
     activations
    0.46
     pairwise
    0.45
    Activations Density 0.421%

    No Known Activations