© 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. 36945
    Prev
    Next
    INDEX
    Explanations

    news article context

    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
     -
    0.57
     de
    0.49
     (
    0.45
     -(
    0.44
    -
    0.43
     practic
    0.42
     sino
    0.42
     gên
    0.42
     marshal
    0.41
    ing
    0.41
    POSITIVE LOGITS
    友達
    0.44
     몇
    0.44
    某种
    0.42
     बुरी
    0.41
    音声
    0.41
    ʇ
    0.41
    知道
    0.41
    某个
    0.40
    曙
    0.40
    вить
    0.39
    Activations Density 0.001%

    No Known Activations