© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13953
    Prev
    Next
    INDEX
    Explanations

    "do you believe"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     uma
    0.66
     pekerjaan
    0.64
     algum
    0.64
     товары
    0.64
     doar
    0.63
     lampu
    0.60
     piers
    0.59
    .¹
    0.59
     pamię
    0.59
     kandungan
    0.59
    POSITIVE LOGITS
     Huyền
    0.51
    stin
    0.50
    ơ
    0.50
    ﻞ
    0.49
     दक्षिण
    0.49
    pubescens
    0.49
    ਟ
    0.49
    ADELPHIA
    0.48
     Nxc
    0.47
    桃園
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.