© 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. 111870
    Prev
    Next
    INDEX
    Explanations

    romance scams

    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
    лли
    0.57
    惮
    0.55
    榃
    0.53
     вещества
    0.51
     élargies
    0.50
     সক
    0.49
     ограничения
    0.49
     মুক্তিব
    0.48
     слу
    0.48
     нацыяна
    0.48
    POSITIVE LOGITS
    A
    0.66
    5
    0.66
    en
    0.62
    3
    0.60
    4
    0.59
    am
    0.59
    :
    0.59
    6
    0.59
     that
    0.57
    H
    0.57
    Activations Density 0.003%

    No Known Activations