© 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. 12711
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and subsequent nouns

    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
    वर्स
    2.04
    뀌
    1.89
    Whitespace
    1.80
     useStyles
    1.76
    د
    1.73
    ટ
    1.72
    esm
    1.71
    ಶ್ರ
    1.69
    dnn
    1.69
    preprocessing
    1.69
    POSITIVE LOGITS
     electric
    2.11
     accessories
    1.89
    電気
    1.88
    丁寧
    1.84
     lighting
    1.77
     кількість
    1.76
     susp
    1.75
    まとめ
    1.74
     interesting
    1.68
    )|$(
    1.68
    Activations Density 0.045%

    No Known Activations