© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219080
    Prev
    Next
    INDEX
    Explanations

    polymeric forms

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

    negative states and historical contexts

    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_262k_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
    гово
    0.52
    Tex
    0.50
    ᑖ
    0.49
    از
    0.47
    त
    0.47
    Sweep
    0.46
    س
    0.45
    વે
    0.45
    தியே
    0.45
    Novel
    0.44
    POSITIVE LOGITS
     currentIndex
    0.46
     โม
    0.45
     गोइंग
    0.44
    主教
    0.43
     সম্ভাবনা
    0.43
     trener
    0.43
     Yann
    0.42
     entrenamiento
    0.42
     Baghdad
    0.41
     Gut
    0.41
    Activations Density 0.000%

    No Known Activations