© 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. 13450
    Prev
    Next
    INDEX
    Explanations

    Caribbean and programming

    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
    ्ज
    2.36
    anyang
    2.28
    ingles
    2.23
    ㅊ
    2.20
    ेच्छा
    2.18
    alka
    2.17
    acional
    2.14
    껭
    2.14
     inlets
    2.13
    ப்பே
    2.13
    POSITIVE LOGITS
    ्यर्थ
    2.19
    Sent
    2.10
    udit
    2.07
    {}".
    2.06
    {}",
    2.05
    목
    2.04
    جم
    2.03
    ദ്ധതി
    1.96
    ‫
    1.96
    િટ
    1.92
    Activations Density 0.005%

    No Known Activations