© 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. 48601
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    ACL, AR, child, NMR

    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
    প্রশ্ন
    0.46
    :
    0.44
     ngủ
    0.42
     बचाता
    0.41
    雞
    0.41
     chứa
    0.40
     nigra
    0.40
    ):
    0.39
     Glastonbury
    0.39
     எதிரான
    0.39
    POSITIVE LOGITS
    צוני
    0.46
    блі
    0.44
    кмекер
    0.44
     unanimously
    0.44
     単
    0.44
    hacking
    0.44
     회사
    0.43
     aziende
    0.43
    ಪಟ್ಟ
    0.43
     vowed
    0.43
    Activations Density 0.000%

    No Known Activations