© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 48889
    Prev
    Next
    INDEX
    Explanations

    have then article or quantity

    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
     Youtube
    0.52
     yng
    0.50
     chr
    0.45
     Brothers
    0.45
     würde
    0.45
     før
    0.44
     youtube
    0.44
     레
    0.44
     gyak
    0.43
     Changel
    0.43
    POSITIVE LOGITS
     responsabilità
    0.45
    літи
    0.43
     ব্যথা
    0.43
    ಪ್ಪು
    0.43
     स्वास्थ्य
    0.42
    ashed
    0.41
    iduciary
    0.40
    핞
    0.40
    आपका
    0.40
    สุขภาพ
    0.40
    Activations Density 0.040%

    No Known Activations