© 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. 239998
    Prev
    Next
    INDEX
    Explanations

    wanted him, too quickly, comparison chart

    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
     are
    0.56
     malay
    0.52
     doj
    0.50
     remed
    0.49
     malef
    0.48
     Verv
    0.48
     contend
    0.48
    /*
    0.47
     unir
    0.47
    ddd
    0.47
    POSITIVE LOGITS
    ан
    0.49
    خ
    0.49
    ôm
    0.48
    وید
    0.48
    andra
    0.47
    withdrawal
    0.46
    των
    0.44
    étant
    0.44
    élim
    0.44
    imp
    0.44
    Activations Density 0.001%

    No Known Activations