© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7125
    Prev
    Next
    INDEX
    Explanations

    tax implications, PDF settings, US action

    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
    izont
    1.87
    anzen
    1.78
    ючись
    1.73
    ників
    1.71
    ('../../
    1.65
    =/
    1.62
    থাৎ
    1.62
    仕上げ
    1.60
    の子
    1.58
    করিতে
    1.58
    POSITIVE LOGITS
     tuổi
    1.12
    <0x8F>
    1.11
     cáo
    1.10
    mb
    1.09
    it
    1.08
     kali
    1.08
    ร่
    1.07
    这么
    1.05
     official
    1.04
     sh
    1.04
    Activations Density 0.000%

    No Known Activations