© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10892
    Prev
    Next
    INDEX
    Explanations

    numbers and phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curvas
    0.37
    жду
    0.36
    тона
    0.36
     preis
    0.35
     rozs
    0.34
    イ
    0.34
    vati
    0.34
     änd
    0.34
    দাম
    0.34
     معمول
    0.33
    POSITIVE LOGITS
     Legislature
    0.41
     Zoological
    0.39
    Subscriber
    0.38
     Subscriber
    0.38
     Niger
    0.38
    舢
    0.37
     niger
    0.37
    शिलाजीत
    0.37
     Nile
    0.36
    Blockchain
    0.36
    Activations Density 0.168%

    No Known Activations