© 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. 14057
    Prev
    Next
    INDEX
    Explanations

    factory and function definitions

    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
     Intelligence
    1.35
     Security
    1.34
     Information
    1.32
     الح
    1.29
    𝑐
    1.29
    <0xEF>
    1.25
     Compar
    1.24
     صف
    1.24
     Diagnosis
    1.23
    ed
    1.22
    POSITIVE LOGITS
    PosZ
    1.81
    특히
    1.78
     посети
    1.74
    resultados
    1.73
    ancouver
    1.67
    northern
    1.66
     deliverables
    1.66
    ਓ
    1.64
    <unused1921>
    1.64
    dcs
    1.63
    Activations Density 0.000%

    No Known Activations