© 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. 13548
    Prev
    Next
    INDEX
    Explanations

    you are not alone

    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
    itares
    0.89
     गरीबी
    0.88
    paque
    0.82
    /∂
    0.82
    ærk
    0.81
    into
    0.80
    ahanan
    0.80
    eldo
    0.79
    klahoma
    0.78
    罫
    0.78
    POSITIVE LOGITS
    數量
    1.75
     number
    1.59
    数目
    1.58
     количества
    1.58
     Number
    1.56
    数量
    1.54
     NUMBER
    1.53
    Number
    1.53
     количество
    1.51
     jumlah
    1.49
    Activations Density 0.224%

    No Known Activations