© 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. 31-GEMMASCOPE-2-RES-262K
    7. 53073
    Prev
    Next
    INDEX
    Explanations

    real return

    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_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
    專業
    0.39
    いが
    0.39
     asimismo
    0.38
    芽
    0.38
     également
    0.38
    াদা
    0.37
     benchmarking
    0.37
     معیار
    0.36
    観
    0.36
     кварта
    0.36
    POSITIVE LOGITS
     enfon
    0.41
    mesine
    0.37
    ześ
    0.37
    nows
    0.37
    rays
    0.36
    retched
    0.35
     regreso
    0.35
     studenti
    0.35
     Pupp
    0.35
     Fransiya
    0.35
    Activations Density 0.001%

    No Known Activations