Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 382
    Prev
    Next
    INDEX
    Explanations

    the U position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.74
    EnglishMarks
    0.56
    ل
    0.54
     phare
    0.53
    جميع
    0.51
     milyen
    0.51
    תה
    0.50
    Teste
    0.50
    Dtls
    0.49
    an
    0.49
    POSITIVE LOGITS
     to
    1.34
     at
    0.84
     be
    0.82
     by
    0.75
     it
    0.72
     that
    0.68
     are
    0.66
     (
    0.61
     t
    0.60
     of
    0.59
    Activations Density 1.927%

    No Known Activations