© 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. 7010
    Prev
    Next
    INDEX
    Explanations

    memories

    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
    너지
    2.01
    na
    1.93
    nal
    1.91
    ny
    1.84
    nie
    1.78
    wart
    1.77
     w
    1.77
    iaus
    1.74
    nya
    1.73
     sow
    1.73
    POSITIVE LOGITS
     fondly
    2.42
    били
    2.41
    闱
    2.38
    োষণ
    2.38
     lluvias
    2.30
    曲线
    2.29
    вать
    2.26
     представляют
    2.25
     paroi
    2.24
     searing
    2.24
    Activations Density 0.219%

    No Known Activations