© 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. 16-GEMMASCOPE-2-RES-262K
    7. 26917
    Prev
    Next
    INDEX
    Explanations

    C++ descriptions

    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_16_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
    𝗱
    0.89
    taro
    0.89
     dậy
    0.87
    d
    0.82
    gimento
    0.79
     від
    0.79
     disgruntled
    0.79
     гне
    0.77
     calam
    0.77
     livelli
    0.77
    POSITIVE LOGITS
     I
    1.20
    uk
    1.13
    hed
    0.93
    é
    0.91
    are
    0.90
    op
    0.89
    ik
    0.88
    uz
    0.85
    im
    0.83
     is
    0.83
    Activations Density 0.006%

    No Known Activations