© 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. 64727
    Prev
    Next
    INDEX
    Explanations

    creation and generating

    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
    "
    0.72
    *
    0.54
    O
    0.50
    G
    0.49
    ک
    0.49
    /
    0.47
    ^*
    0.47
    합니다
    0.46
    母
    0.46
    öt
    0.44
    POSITIVE LOGITS
     dijel
    0.50
     உருவாக்கு
    0.48
     generando
    0.48
     zaten
    0.48
     creando
    0.47
     разработ
    0.46
     ಏಕೆ
    0.46
     faibles
    0.46
     creare
    0.45
     вече
    0.44
    Activations Density 0.015%

    No Known Activations