© 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. 12395
    Prev
    Next
    INDEX
    Explanations

    names in forbes articles

    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
    uggest
    1.50
     finished
    1.48
     diagnose
    1.46
     chiamato
    1.40
     disappointed
    1.38
     PAID
    1.37
    n
    1.36
     attribut
    1.34
     repaid
    1.34
    یل
    1.34
    POSITIVE LOGITS
    嘩
    1.78
    vodu
    1.65
    ıyoruz
    1.64
     সৌম
    1.64
     solidar
    1.61
    ğa
    1.56
    мб
    1.56
     आह्वान
    1.54
    Ту
    1.53
    钲
    1.53
    Activations Density 0.077%

    No Known Activations