© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63943
    Prev
    Next
    INDEX
    Explanations

    extract data, triples, designer

    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_65k_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
     스테
    0.52
     कोक
    0.47
     מק
    0.46
     subsection
    0.46
    inguistic
    0.46
     하며
    0.45
    ochastic
    0.44
    敉
    0.44
     ROI
    0.43
     እንዴት
    0.43
    POSITIVE LOGITS
    жит
    0.47
    حت
    0.46
    cht
    0.46
     Aj
    0.45
     florals
    0.45
    ضة
    0.45
    htu
    0.45
     Start
    0.45
    ี่ยว
    0.44
    。
    0.43
    Activations Density 0.001%

    No Known Activations