© 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-16K
    7. 12621
    Prev
    Next
    INDEX
    Explanations

    principal plus your fees

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

    principal and interest

    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_16k_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
    ខ្សែ
    0.52
     اکثریت
    0.47
    ურთიერთ
    0.43
    々は
    0.42
     언급
    0.41
     ខ
    0.41
    öffentlichung
    0.41
     बोलेंगे
    0.41
    纮
    0.41
    的心
    0.41
    POSITIVE LOGITS
    AndTime
    0.41
     forfeiture
    0.40
     to
    0.40
    渚
    0.39
     with
    0.38
     embassy
    0.38
     Embassy
    0.38
     whereupon
    0.37
     сро
    0.36
     шан
    0.36
    Activations Density 0.001%

    No Known Activations