© 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-65K
    7. 5103
    Prev
    Next
    INDEX
    Explanations

    Bolivia Maryland sections narcotics scuba

    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_65k_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
    着用
    0.41
    ृत
    0.40
    iri
    0.39
    ı
    0.38
    ṛ
    0.38
    >\
    0.38
     সৈ
    0.38
    :>
    0.38
    idi
    0.37
    逝
    0.37
    POSITIVE LOGITS
     Bolivia
    0.46
     sections
    0.44
     narcotics
    0.43
     kilow
    0.41
     understandably
    0.40
     scuba
    0.39
     oversaw
    0.39
    <unused1100>
    0.39
     Maryland
    0.39
    <unused625>
    0.39
    Activations Density 0.006%

    No Known Activations