© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2421
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    2
    0.63
    4
    0.56
    5
    0.56
    3
    0.55
     if
    0.54
    1
    0.52
    if
    0.51
    7
    0.51
    .
    0.49
     or
    0.48
    POSITIVE LOGITS
    用户
    0.50
    username
    0.50
    颜值
    0.49
    iscono
    0.47
     tahmin
    0.46
    悱
    0.46
    宽松
    0.46
    最初に
    0.46
     osobe
    0.46
    㞰
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.