© 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. 159053
    Prev
    Next
    INDEX
    Explanations

    sales proposal

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

    pitch deck

    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
    :
    0.50
    ,
    0.46
    ソニック
    0.45
     shaft
    0.44
     {
    0.43
     lancement
    0.43
     Lookout
    0.42
     Cliffs
    0.42
    /
    0.41
    =
    0.41
    POSITIVE LOGITS
     용
    0.59
    غة
    0.48
    賚
    0.48
    이는
    0.47
    чатки
    0.47
    מ
    0.47
     שה
    0.46
     שני
    0.46
    čnosti
    0.46
    जिसे
    0.46
    Activations Density 0.001%

    No Known Activations