© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6726
    Prev
    Next
    INDEX
    Explanations

    easily removed or irrelevant

    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
    Dots
    0.46
    RTC
    0.40
    Seamless
    0.40
    '_
    0.40
    ﹁
    0.39
    Immediate
    0.39
     jurisdictional
    0.39
     RTC
    0.38
    ∆
    0.38
     adecuadas
    0.37
    POSITIVE LOGITS
     false
    0.63
    false
    0.50
     fals
    0.49
     facilmente
    0.49
     magari
    0.47
     False
    0.46
     fácilmente
    0.46
     conceivably
    0.46
     거짓
    0.46
     falsely
    0.46
    Activations Density 0.214%

    No Known Activations