© 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. 17274
    Prev
    Next
    INDEX
    Explanations

    reproduce results

    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
    is
    1.11
    i
    0.94
    é
    0.90
     défin
    0.88
    I
    0.85
    .");
    0.83
    enquête
    0.82
     distrib
    0.82
    message
    0.82
     contrib
    0.80
    POSITIVE LOGITS
     reproduction
    1.09
    ين
    1.04
     Reproduction
    0.94
     reproduced
    0.93
     Reproduced
    0.93
     reproducing
    0.93
    ной
    0.91
    я
    0.90
    ции
    0.86
     Reprodu
    0.85
    Activations Density 0.004%

    No Known Activations