© 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. 47872
    Prev
    Next
    INDEX
    Explanations

    talking about community and company

    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
    仍然
    0.41
     criminal
    0.40
    Berikut
    0.40
     Mois
    0.40
     Hamas
    0.39
     F
    0.39
     সম্পূর্ণরূপে
    0.39
     Ansch
    0.38
     Moscou
    0.38
    畜
    0.38
    POSITIVE LOGITS
     appreci
    0.46
     appréci
    0.44
    蓣
    0.42
     यूट्यूब
    0.40
    జె
    0.40
    orie
    0.40
    alic
    0.40
     moderately
    0.40
    㑯
    0.40
     кора
    0.39
    Activations Density 0.032%

    No Known Activations