© 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. 137159
    Prev
    Next
    INDEX
    Explanations

    following preposition or determiner

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

    duty cycle

    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
     pkt
    0.52
    d
    0.50
     appreciate
    0.48
     disciple
    0.48
    bong
    0.47
     remod
    0.47
    kiem
    0.46
     desg
    0.46
    pictureBox
    0.46
    糀
    0.46
    POSITIVE LOGITS
    เสริม
    0.50
     Morg
    0.49
    iczne
    0.45
    北部
    0.44
     Northumberland
    0.44
     Ragnar
    0.44
    ics
    0.42
     Magnus
    0.42
    ত্যাগ
    0.42
    )':
    0.41
    Activations Density 0.000%

    No Known Activations