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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14427
    Prev
    Next
    INDEX
    Explanations

    dialogue start quote

    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
     oppression
    1.33
    ゚
    1.26
     spindles
    1.25
     manipulation
    1.24
    ycles
    1.22
     movement
    1.19
    ಿಗಳ
    1.15
    oplasm
    1.12
     injustice
    1.11
     і
    1.11
    POSITIVE LOGITS
     similaire
    1.35
    geojson
    1.32
    Radar
    1.31
     pih
    1.27
     Wetlands
    1.23
     proyect
    1.21
    WebGL
    1.20
     correspondió
    1.17
     gambar
    1.17
     यादगार
    1.17
    Activations Density 0.043%

    No Known Activations