© 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. 53378
    Prev
    Next
    INDEX
    Explanations

    few-shot examples and pattern understanding

    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
    вес
    0.51
     Coolidge
    0.47
     ใหญ่
    0.46
    ใหญ่
    0.45
    ent
    0.44
    ;$
    0.44
     Admiralty
    0.44
    Bound
    0.44
    😧
    0.44
    ultan
    0.44
    POSITIVE LOGITS
    デ
    0.44
     stepped
    0.43
     maths
    0.41
    体现
    0.41
     rene
    0.41
     jumper
    0.41
     पिन
    0.41
     cyl
    0.41
     pin
    0.41
     paperwork
    0.40
    Activations Density 0.005%

    No Known Activations