© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 15003
    Prev
    Next
    INDEX
    Explanations

    holy city, land, grail, Trinity, Roman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    Biografia
    2.49
    DebugSymbols
    2.33
    اعری
    2.25
     pulumi
    2.24
    uestos
    2.24
    ភ
    2.24
    =@@
    2.23
    ExpireTime
    2.23
    ﻲ
    2.21
    कोर्ट
    2.21
    POSITIVE LOGITS
    sam
    3.31
    ا
    3.27
    s
    3.26
    u
    3.23
    sus
    2.69
    tj
    2.62
    an
    2.57
    h
    2.56
    szak
    2.54
    sang
    2.52
    Activations Density 0.013%

    No Known Activations