© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 132153
    Prev
    Next
    INDEX
    Explanations

    language linkage

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

    beat drops

    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
    交易所
    0.57
    карбо
    0.51
    🤙
    0.50
    ◌
    0.47
    uttle
    0.45
    了一个
    0.45
    ziła
    0.45
    ➡️
    0.44
    tiket
    0.44
    ⭐️
    0.44
    POSITIVE LOGITS
    ିକ
    0.49
     LEAD
    0.46
    付近
    0.45
     सड़कें
    0.44
    熱
    0.43
     reaching
    0.43
     JUNE
    0.43
     encompassing
    0.42
     JULY
    0.42
     LETTER
    0.42
    Activations Density 0.002%

    No Known Activations