© 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. 12115
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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
    am
    1.23
    ah
    1.00
    p
    0.98
     \&
    0.91
    ла
    0.86
    ai
    0.86
    ad
    0.84
    he
    0.76
     Ε
    0.75
    indruck
    0.74
    POSITIVE LOGITS
    ت
    1.04
    ä
    0.95
    ों
    0.94
    க
    0.93
    る
    0.93
    .’
    0.93
    டன்
    0.93
    ۴
    0.92
    dır
    0.91
    ERS
    0.90
    Activations Density 0.027%

    No Known Activations