© 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-262K
    7. 44789
    Prev
    Next
    INDEX
    Explanations

    auf followed by a noun phrase

    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_262k_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
    ড়
    0.45
    разде
    0.41
     banderas
    0.40
    о
    0.40
     от
    0.39
     крупных
    0.38
    of
    0.38
    permit
    0.38
    着
    0.38
    by
    0.38
    POSITIVE LOGITS
     начин
    0.54
     manière
    0.54
     wijze
    0.52
     način
    0.47
    നില
    0.47
     şekilde
    0.47
    方式
    0.46
     τρόπο
    0.46
     måde
    0.45
     základě
    0.45
    Activations Density 0.003%

    No Known Activations