© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 14608
    Prev
    Next
    INDEX
    Explanations

    Sophistication and soundsets

    np_acts-logits-general · gemini-2.5-flash-lite

    recursion and approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    白
    0.53
    黑
    0.50
     variado
    0.49
    ני
    0.49
     unpre
    0.48
    伐
    0.48
    בת
    0.47
    內部
    0.47
    발
    0.47
    寨
    0.47
    POSITIVE LOGITS
    spinal
    0.45
    –
    0.43
    ~/
    0.42
    rade
    0.40
     pants
    0.40
    jø
    0.40
    readthedocs
    0.40
    translational
    0.40
    fails
    0.39
    policy
    0.39
    Activations Density 0.010%

    No Known Activations