© 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. 72897
    Prev
    Next
    INDEX
    Explanations

    assisted living services

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

    its own continued purpose

    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
    ména
    0.50
     имуще
    0.47
     పాల్
    0.47
     кантора
    0.47
    chet
    0.47
    orderDisplay
    0.46
    produk
    0.45
    }";
    0.45
     اجمعين
    0.45
     كلكم
    0.45
    POSITIVE LOGITS
     contrasts
    0.54
     beds
    0.48
     contrasted
    0.47
    FOR
    0.47
    RAR
    0.47
     up
    0.45
    II
    0.44
     backs
    0.43
    NIC
    0.43
    NEW
    0.43
    Activations Density 0.002%

    No Known Activations