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

    Neuronpedia

    Jacobian LensNEW
    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. 63210
    Prev
    Next
    INDEX
    Explanations

    network related terms

    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
     vampires
    0.42
     nowadays
    0.41
     बच्‍
    0.40
    ◠
    0.39
     onderste
    0.38
     Loretta
    0.38
     niñas
    0.38
     murderers
    0.37
    ᐢ
    0.37
     બાળકો
    0.36
    POSITIVE LOGITS
     участка
    0.45
     Перейти
    0.38
    брав
    0.38
    আন্ত
    0.37
     sarebbe
    0.36
    éal
    0.35
    imageUrl
    0.35
     llega
    0.35
    erebbe
    0.35
     synovial
    0.35
    Activations Density 0.002%

    No Known Activations