© 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. 163018
    Prev
    Next
    INDEX
    Explanations

    wine and communications

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

    complex and multi-dimensional

    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
    '
    0.54
     agent
    0.54
     które
    0.50
     alloy
    0.50
     cd
    0.46
     aut
    0.46
     অর্থ
    0.46
     Reproduced
    0.46
     agents
    0.46
     deceased
    0.46
    POSITIVE LOGITS
     brimming
    0.54
    溢
    0.53
    Questo
    0.49
     abordagem
    0.48
     Teixeira
    0.48
     sfida
    0.47
    Ban
    0.47
    込み
    0.46
     الجديدة
    0.46
     dispuestos
    0.45
    Activations Density 0.001%

    No Known Activations