© 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. 31-GEMMASCOPE-2-RES-262K
    7. 202924
    Prev
    Next
    INDEX
    Explanations

    prudential, transaction, proportion

    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_31_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
     R
    0.47
    ळे
    0.46
    vers
    0.45
     North
    0.44
     Land
    0.42
    ogn
    0.42
     Pro
    0.41
     Pet
    0.41
     PHILLIPS
    0.41
     L
    0.40
    POSITIVE LOGITS
    エネルギー
    0.49
     encapsulates
    0.49
     videojuegos
    0.49
    イタリア
    0.48
     penetrates
    0.47
     outperforms
    0.47
     impulsar
    0.46
     dehydrogen
    0.46
     exudes
    0.46
     derives
    0.45
    Activations Density 0.005%

    No Known Activations