© 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. 12258
    Prev
    Next
    INDEX
    Explanations

    captivating / compelling / attracting / to entice

    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
     或
    1.68
    或其他
    1.56
    或是
    1.55
    ක්
    1.46
     मृ
    1.40
    향
    1.40
     किंवा
    1.39
    ෙකු
    1.38
    賖
    1.36
    이나
    1.34
    POSITIVE LOGITS
     contamos
    1.62
     Paola
    1.56
     bukan
    1.42
     hablamos
    1.41
     Toma
    1.38
    pp
    1.36
    erna
    1.35
    aaaa
    1.34
     usando
    1.34
    ções
    1.34
    Activations Density 0.128%

    No Known Activations