© 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. 11934
    Prev
    Next
    INDEX
    Explanations

    crime, alternate realities, independence

    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
     presently
    0.89
     constituents
    0.87
    т
    0.86
    মোট
    0.84
     allong
    0.83
     volta
    0.83
    থের
    0.83
     entren
    0.81
    ా
    0.81
    সপ
    0.81
    POSITIVE LOGITS
     공유
    1.52
     추가
    1.47
     변경
    1.43
     تغییر
    1.41
     옆
    1.39
     했던
    1.38
    ▋
    1.37
    修改
    1.35
     சுரே
    1.32
     너무
    1.32
    Activations Density 0.000%

    No Known Activations