© 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. 251995
    Prev
    Next
    INDEX
    Explanations

    most important

    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
    Ｂ
    0.50
    뤼
    0.49
    イント
    0.46
    Geolocation
    0.46
    尊重
    0.46
    ０
    0.46
    ROHAN
    0.46
     аргу
    0.45
    НА
    0.45
    㑒
    0.45
    POSITIVE LOGITS
    claimed
    0.52
     eviden
    0.51
     একটি
    0.50
     held
    0.49
     scar
    0.49
    tro
    0.48
     Sud
    0.47
    segment
    0.47
     an
    0.46
     jedna
    0.46
    Activations Density 0.001%

    No Known Activations