© 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. 630
    Prev
    Next
    INDEX
    Explanations

    qualities and descriptions

    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
    夫婦
    2.17
    atical
    2.06
    vir
    2.06
    ườ
    2.06
    édia
    2.03
    젝트
    2.02
     ụ
    2.01
    꼴
    2.00
    ẹt
    1.99
    ALOG
    1.96
    POSITIVE LOGITS
    สบาย
    2.10
     restful
    2.05
    惬
    1.99
    谧
    1.93
     tranquillity
    1.92
     dold
    1.92
     tranquility
    1.85
    qquad
    1.80
     nghỉ
    1.79
     repose
    1.76
    Activations Density 1.073%

    No Known Activations