© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27372
    Prev
    Next
    INDEX
    Explanations

    the followed by specific entities

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptive words after "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    tesy
    0.42
     Luís
    0.41
    ί
    0.40
    ähn
    0.39
     Haines
    0.38
    ī
    0.38
    将其
    0.38
     Louise
    0.38
     Werner
    0.37
    ೮
    0.37
    POSITIVE LOGITS
    био
    0.43
    这些人
    0.42
     вообще
    0.42
     этих
    0.40
     लागे
    0.40
     bhakti
    0.40
     ambience
    0.39
     आल
    0.39
    ంతా
    0.39
     terse
    0.38
    Activations Density 0.002%

    No Known Activations