© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14247
    Prev
    Next
    INDEX
    Explanations

    presence and location

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

    here to help

    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_16k_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
     postpone
    0.49
    editable
    0.46
     postponement
    0.45
     ……
    0.42
    aksha
    0.40
     postponed
    0.39
     clothe
    0.39
    ヌ
    0.39
    ……
    0.39
     correspondences
    0.39
    POSITIVE LOGITS
     witnessing
    0.50
     شاهد
    0.50
     grabando
    0.49
     menyaksikan
    0.47
    常に
    0.46
     সাক্ষী
    0.46
     guiding
    0.45
     richtigen
    0.45
    人も
    0.44
    噰
    0.44
    Activations Density 0.400%

    No Known Activations