© 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. 15900
    Prev
    Next
    INDEX
    Explanations

    numbers followed by countable items

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

    ratings up to 5

    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
     the
    0.41
     E
    0.40
     also
    0.40
     G
    0.36
    hetically
    0.35
     h
    0.35
     associations
    0.34
     mileage
    0.34
    MAG
    0.34
    DOI
    0.34
    POSITIVE LOGITS
     incluyendo
    0.64
     incluindo
    0.61
     gồm
    0.60
     včetně
    0.55
    ৩
    0.54
     وذلك
    0.54
     सहित
    0.52
    其中包括
    0.51
     котором
    0.51
     puluh
    0.50
    Activations Density 0.021%

    No Known Activations