© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12463
    Prev
    Next
    INDEX
    Explanations

    .com domains followed by path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    .}\
    1.24
    zenesulf
    1.22
     소련
    1.14
    ataires
    1.11
    ສຸດ
    1.11
     hỗn
    1.10
     Angleterre
    1.10
     ⿰
    1.10
    ஸ்வர
    1.09
    тература
    1.07
    POSITIVE LOGITS
     ob
    0.97
     excellent
    0.93
     excel
    0.90
     conducting
    0.87
    Om
    0.86
    الت
    0.86
    rad
    0.85
     wearables
    0.85
    Res
    0.83
     workflows
    0.83
    Activations Density 0.232%

    No Known Activations