© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184150
    Prev
    Next
    INDEX
    Explanations

    specific phrases and sequences

    np_acts-logits-general · gemini-2.5-flash-lite

    important notes for adults

    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_31_width_262k_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
    StoredKeys
    0.55
    큥
    0.51
    噘
    0.49
    一直在
    0.46
     Кры
    0.46
    Zawodnik
    0.45
     ক্ষু
    0.45
    沿
    0.44
    carry
    0.43
    ুয়ারি
    0.43
    POSITIVE LOGITS
     at
    0.57
     n
    0.53
     !
    0.52
     printer
    0.51
     SERVER
    0.50
     yh
    0.50
     c
    0.49
     !\
    0.49
     optimal
    0.49
     on
    0.49
    Activations Density 0.001%

    No Known Activations