© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 707
    Prev
    Next
    INDEX
    Explanations

    editor scripting and programming code

    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
     meminta
    2.94
     UWGM
    2.92
     objRequest
    2.87
     aşağıdaki
    2.87
     hasonló
    2.86
     strListName
    2.86
    𒊺
    2.83
    𒉈
    2.82
    <unused1394>
    2.81
    𒅀
    2.81
    POSITIVE LOGITS
    ne
    1.39
    -
    1.32
    h
    1.28
    ic
    1.27
    al
    1.27
    ind
    1.26
    b
    1.25
    im
    1.25
    av
    1.25
    ed
    1.25
    Activations Density 8.512%

    No Known Activations