© 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. 20656
    Prev
    Next
    INDEX
    Explanations

    discord bloom

    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
     Moovit
    0.51
     recib
    0.50
     recibir
    0.50
     ক্ষয়ক্ষতি
    0.46
    arquivo
    0.45
    ाना
    0.44
    ᱝ
    0.44
     marah
    0.44
    ത്സ
    0.43
     charles
    0.42
    POSITIVE LOGITS
     ㅣ
    0.45
    ürz
    0.41
     ㅇ
    0.40
     背
    0.40
    arium
    0.39
     জন্যে
    0.39
    㓡
    0.39
    的可
    0.39
     강조
    0.39
    °,
    0.39
    Activations Density 0.005%

    No Known Activations