© 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. 248484
    Prev
    Next
    INDEX
    Explanations

    expressing potential states (you may/can/are)

    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
    阿
    0.49
    нце
    0.48
     tees
    0.47
    álen
    0.47
     कमलेश
    0.46
    Salman
    0.45
     elution
    0.44
    uerra
    0.44
    柔
    0.43
    дали
    0.43
    POSITIVE LOGITS
    ata
    0.52
    tr
    0.50
     موارد
    0.46
    erex
    0.46
    ih
    0.46
    th
    0.45
     संभावित
    0.45
    trx
    0.45
     बेश
    0.45
     می‌باشد
    0.44
    Activations Density 0.002%

    No Known Activations