© 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. 16-GEMMASCOPE-2-RES-262K
    7. 28012
    Prev
    Next
    INDEX
    Explanations

    italian preposition di

    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_16_width_262k_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
    কে
    1.27
     to
    1.22
    ية
    1.13
    на
    1.08
    에
    1.05
    ia
    1.02
    此同时
    1.00
     profondes
    0.90
    瀰
    0.89
    ly
    0.88
    POSITIVE LOGITS
    in
    1.45
     di
    1.41
    ר
    1.35
    er
    1.27
    ILL
    1.27
    s
    1.27
     renormal
    1.23
    Di
    1.22
    l
    1.21
    sheets
    1.17
    Activations Density 0.007%

    No Known Activations