© 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. 1716
    Prev
    Next
    INDEX
    Explanations

    imperative verbs followed by your/yer

    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
    eksiyon
    1.47
     .=
    1.39
     kwargs
    1.34
    ()*
    1.28
    ::$
    1.26
    .$.
    1.25
    acariy
    1.25
     ['$
    1.24
    dcs
    1.22
     Optimal
    1.20
    POSITIVE LOGITS
     Yourself
    1.80
     yourself
    1.76
     your
    1.66
     yourselves
    1.56
    vole
    1.53
    yourself
    1.51
     thine
    1.51
     Your
    1.49
    你的
    1.45
     thy
    1.44
    Activations Density 0.770%

    No Known Activations