© 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. 505
    Prev
    Next
    INDEX
    Explanations

    adverbial endings

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

    Sed do eiusmod

    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
    बोध
    0.29
    <unused43>
    0.28
     religiosa
    0.28
     religieux
    0.28
     thisTrack
    0.28
     devotional
    0.28
    роў
    0.28
     religi
    0.28
     religiosas
    0.27
     réglement
    0.27
    POSITIVE LOGITS
     at
    0.29
    一
    0.25
     head
    0.25
     신
    0.24
    start
    0.24
    0.24
     start
    0.23
     the
    0.23
    zet
    0.23
     fast
    0.22
    Activations Density 0.001%

    No Known Activations