© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13180
    Prev
    Next
    INDEX
    Explanations

    ```jsxuseState declarations

    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
     cara
    1.72
    吝
    1.66
     eng
    1.62
    inink
    1.60
    ษฐ
    1.58
    tough
    1.55
    inspired
    1.54
    artist
    1.54
    me
    1.51
    in
    1.50
    POSITIVE LOGITS
    świad
    2.27
     NodeType
    2.27
    ထ
    2.12
    狀
    2.10
    荲
    2.07
    িয়োগ
    2.06
    ድረግ
    2.06
    சே
    2.05
    𝙛
    2.05
    ໃຫ
    2.05
    Activations Density 0.005%

    No Known Activations