© 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. 3864
    Prev
    Next
    INDEX
    Explanations

    based on a singular source

    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
     ಸಲ
    0.45
    GEBURTS
    0.45
    用於
    0.42
     ምግብ
    0.42
    𝚇
    0.42
     bhavanti
    0.41
     प्रकाशन
    0.41
     பேசு
    0.41
     обучение
    0.41
     contentService
    0.41
    POSITIVE LOGITS
     solely
    0.59
     entirely
    0.57
     a
    0.55
     only
    0.52
     ainult
    0.52
     tikai
    0.52
    using
    0.49
     wyłącznie
    0.47
     केवल
    0.46
    \
    0.45
    Activations Density 0.171%

    No Known Activations