© 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. 177812
    Prev
    Next
    INDEX
    Explanations

    card ranks and states

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

    numpy code manipulation

    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
    لو
    0.49
    money
    0.46
    俭
    0.46
    قول
    0.45
    س
    0.45
     اچھی
    0.45
    钱
    0.44
    同样
    0.44
    電流
    0.44
    نیم
    0.44
    POSITIVE LOGITS
    oniazid
    0.61
     feces
    0.53
     subcut
    0.52
     apical
    0.50
     birt
    0.48
     oligonucleotide
    0.48
     goa
    0.47
     ™
    0.47
     sputum
    0.47
     aiguë
    0.46
    Activations Density 0.001%

    No Known Activations