© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 6232
    Prev
    Next
    INDEX
    Explanations

    passion and interest

    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
     handicrafts
    0.39
    pha
    0.38
    pg
    0.36
     Father
    0.36
     दर्
    0.35
    지막
    0.35
    釐
    0.35
    ста
    0.34
     t
    0.34
    తం
    0.34
    POSITIVE LOGITS
     autoch
    0.41
     creado
    0.39
    ؏
    0.39
     सो
    0.39
    automat
    0.39
    選び
    0.38
     difficol
    0.38
    莠
    0.37
     ভবিষ্যত
    0.36
    懵
    0.36
    Activations Density 0.004%

    No Known Activations