© 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. 55997
    Prev
    Next
    INDEX
    Explanations

    even / potentially / chestnut / take / problems / the / etc / even / - / leather

    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
     sciences
    0.47
     anesthesia
    0.46
    슘
    0.44
     isoniazid
    0.43
     research
    0.42
     ethics
    0.41
     aspirin
    0.40
     hydrology
    0.39
     anest
    0.39
     fisheries
    0.38
    POSITIVE LOGITS
     ה
    0.51
     групп
    0.49
     اید
    0.47
     Grup
    0.46
     בו
    0.46
    ódigo
    0.45
    㫧
    0.45
     группы
    0.45
     单位
    0.44
    凯
    0.44
    Activations Density 0.001%

    No Known Activations