© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10906
    Prev
    Next
    INDEX
    Explanations

    closing punctuation then word

    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_31_width_16k_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
     How
    0.37
     .
    0.36
     Amid
    0.36
     Because
    0.35
    "
    0.35
     kontakt
    0.34
     "
    0.34
     overcome
    0.34
     E
    0.33
     Are
    0.33
    POSITIVE LOGITS
    мера
    0.43
     જરૂ
    0.43
    的文件
    0.42
    agangan
    0.41
    荩
    0.41
    Golf
    0.40
    deployRoot
    0.40
    STOCK
    0.40
     커피
    0.40
    Kinder
    0.40
    Activations Density 0.020%

    No Known Activations