© 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. 48506
    Prev
    Next
    INDEX
    Explanations

    fell out

    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
     tomon
    0.42
    지
    0.42
     jurisdic
    0.42
     ۱
    0.41
     குறிப்பிட்ட
    0.41
    ⚧
    0.41
     انع
    0.41
    '&&
    0.40
     విషయ
    0.40
     تحليل
    0.40
    POSITIVE LOGITS
     Despite
    0.50
     tetapi
    0.43
     Ada
    0.43
     военной
    0.43
     Несмотря
    0.41
    搽
    0.41
     без
    0.41
     Such
    0.40
     Paddle
    0.40
     Sing
    0.40
    Activations Density 0.014%

    No Known Activations