© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3392
    Prev
    Next
    INDEX
    Explanations

    European Commission

    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_7_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
    loading
    1.34
    (
    1.26
    icted
    1.24
    )
    1.21
     blinding
    1.20
    pressing
    1.19
     compacted
    1.18
     scorched
    1.18
    ho
    1.16
    sick
    1.15
    POSITIVE LOGITS
     endereco
    1.97
     appBar
    1.86
    ֮
    1.72
     CharPtr
    1.71
     初始化
    1.69
     resetCounters
    1.69
     grundsätzlich
    1.68
     updateConfirm
    1.66
     tagReport
    1.64
     pInBuffer
    1.63
    Activations Density 0.278%

    No Known Activations