© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 103
    Prev
    Next
    INDEX
    Explanations

    Microsoft, OpenAI, YouTube products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     and
    0.29
     And
    0.29
     which
    0.25
     ,
    0.25
     whose
    0.25
    และ
    0.24
    and
    0.24
     etc
    0.23
     -
    0.23
    import
    0.23
    POSITIVE LOGITS
    ależy
    0.23
     гораздо
    0.23
     лучше
    0.22
    utilise
    0.21
    Pued
    0.21
    ется
    0.21
    ства
    0.21
     считает
    0.20
     proporcional
    0.20
     доби
    0.20
    Activations Density 0.315%

    No Known Activations