© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13013
    Prev
    Next
    INDEX
    Explanations

    regardless of

    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
    ργαν
    1.30
    个体
    1.26
    čin
    1.25
     organisations
    1.23
     olur
    1.20
    縄
    1.20
    서울특별시
    1.18
    ülete
    1.18
    극
    1.18
     anxieties
    1.17
    POSITIVE LOGITS
     ا
    1.52
     ك
    1.48
    I
    1.46
     Synchronization
    1.45
     restarting
    1.42
     तीन
    1.38
     ১৩
    1.37
     Defts
    1.33
     لي
    1.33
     دیا۔
    1.32
    Activations Density 0.604%

    No Known Activations