© 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. 248550
    Prev
    Next
    INDEX
    Explanations

    if you want

    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
     RAI
    0.55
    礦
    0.48
    专题
    0.47
     Rizal
    0.47
    萬元
    0.47
     Hinton
    0.46
    bertson
    0.46
    الب
    0.46
     Харків
    0.46
     théor
    0.46
    POSITIVE LOGITS
     wrongfully
    0.48
    ne
    0.48
    ต
    0.48
    ж
    0.47
     wronged
    0.47
    rou
    0.46
    rains
    0.45
    ums
    0.45
    um
    0.44
    aklar
    0.44
    Activations Density 0.001%

    No Known Activations