© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1244
    Prev
    Next
    INDEX
    Explanations

    numbers and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    twenty
    1.02
    thirty
    0.96
    <u>
    0.94
    fifty
    0.93
    二十
    0.89
    approximately
    0.87
    <s>
    0.85
    三十
    0.84
    <strong>
    0.82
    multi
    0.82
    POSITIVE LOGITS
     Wochenende
    0.73
    ロナ
    0.71
    ワイト
    0.69
     commemorating
    0.67
    Ᏹ
    0.66
     septembre
    0.66
     сентября
    0.65
     cGraph
    0.65
    ंटा
    0.64
    悆
    0.64
    Activations Density 0.284%

    No Known Activations