© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3485
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and associated concepts

    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
     раз
    1.56
     હજાર
    1.55
     ומ
    1.54
    affen
    1.51
    BarStyle
    1.48
     swung
    1.46
    气的
    1.46
    气
    1.44
     گرفتن
    1.43
    ೂರು
    1.43
    POSITIVE LOGITS
     mūsų
    1.88
     vaše
    1.77
     vaš
    1.73
     accordance
    1.71
     sesión
    1.70
     nossa
    1.70
     rubrique
    1.70
     ঘটবে
    1.69
    ėl
    1.68
     naše
    1.68
    Activations Density 0.643%

    No Known Activations