© 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. 2131
    Prev
    Next
    INDEX
    Explanations

    divisible by, multiple of, even

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

    divisibility and modulo checks

    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
     പുതിയ
    0.44
     tuz
    0.43
     mieli
    0.43
     مە
    0.42
    Kob
    0.42
    <unused25>
    0.41
     wij
    0.41
     شراب
    0.41
     rejest
    0.41
     allgemeinen
    0.40
    POSITIVE LOGITS
     divisible
    0.61
     fondness
    0.42
     multiples
    0.42
    번째
    0.42
     Rapt
    0.41
     divisor
    0.41
    íb
    0.41
    angent
    0.40
    刮
    0.40
     Cycle
    0.40
    Activations Density 0.001%

    No Known Activations