© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71207
    Prev
    Next
    INDEX
    Explanations

    Scheme, companies, searching, prepare, shape, today

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

    job or web3

    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
    Negative Logits
    最为
    0.47
    itm
    0.46
    FileNotFound
    0.45
    ты
    0.44
    attam
    0.43
    usu
    0.42
    aglia
    0.42
    occ
    0.42
    퉁
    0.42
    agam
    0.41
    POSITIVE LOGITS
     tiden
    0.50
     compro
    0.49
     organizers
    0.46
    AssetDiscovery
    0.46
     wallpapers
    0.46
     SCH
    0.45
     Mā
    0.45
     certeza
    0.45
     verdicts
    0.44
     organizational
    0.44
    Activations Density 0.002%

    No Known Activations