© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15369
    Prev
    Next
    INDEX
    Explanations

    grouping beans and cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outperformed
    1.26
    <unused1030>
    1.24
     impairs
    1.23
    ფორმა
    1.20
     inflicted
    1.18
    <unused2128>
    1.17
    <unused2165>
    1.17
    <unused2107>
    1.15
     adversely
    1.14
    排放
    1.14
    POSITIVE LOGITS
    an
    0.87
     reminder
    0.86
    er
    0.84
    ex
    0.76
    ر
    0.75
    stream
    0.75
    Ang
    0.74
    .
    0.73
    ions
    0.73
     grou
    0.73
    Activations Density 0.001%

    No Known Activations