© 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. 53730
    Prev
    Next
    INDEX
    Explanations

    dealing with relationships and specific entities

    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
    ™,
    0.48
     unscrupulous
    0.46
     বিভিন্ন
    0.46
     unaccount
    0.44
     asa
    0.42
     språk
    0.42
    ]
    0.41
    kish
    0.41
     bv
    0.40
     mengambil
    0.40
    POSITIVE LOGITS
     მო
    0.41
    Consequently
    0.41
     Ceremon
    0.41
     هيا
    0.41
    ڵ
    0.41
    ಲು
    0.40
    ﯾ
    0.40
    فرم
    0.40
    捍
    0.40
     Patrim
    0.39
    Activations Density 0.020%

    No Known Activations