© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13573
    Prev
    Next
    INDEX
    Explanations

    quantity and proportion

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

    counting and selection

    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
     ሁሉ
    0.44
    ዎ
    0.40
     সমস্ত
    0.40
    ทั่ว
    0.40
    锦
    0.40
    вор
    0.39
    юсь
    0.38
    𒂵
    0.38
    šću
    0.37
    рке
    0.37
    POSITIVE LOGITS
     davon
    0.86
     منهم
    0.63
     specifically
    0.62
     diantaranya
    0.61
     whereof
    0.59
     deles
    0.55
     είναι
    0.53
    是對
    0.53
     específicamente
    0.52
     includes
    0.52
    Activations Density 0.226%

    No Known Activations