© 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. 141260
    Prev
    Next
    INDEX
    Explanations

    cross, profiling, voltages, events, mascara, hands, copy

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

    likely outcomes, Russia, Phones, profit

    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
    Negative Logits
    assadors
    0.52
     lintas
    0.51
     chills
    0.51
    हाबाद
    0.49
    સભા
    0.49
     pInBuffer
    0.48
    ᱐
    0.48
     ★★
    0.48
     एस
    0.48
     briefings
    0.47
    POSITIVE LOGITS
    R
    0.48
    祖
    0.45
    Vi
    0.43
    Water
    0.42
    导航
    0.42
    拍摄
    0.42
    >..\
    0.41
    Lonely
    0.41
    Product
    0.41
    收藏
    0.40
    Activations Density 0.000%

    No Known Activations