© 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. 151229
    Prev
    Next
    INDEX
    Explanations

    var. followed by identifier

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

    Go struct definitions

    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
    artner
    0.45
    ==
    0.42
     kalian
    0.42
    azer
    0.40
     azure
    0.40
     ?”
    0.40
    zmq
    0.39
     ?"
    0.39
     Azure
    0.39
    などを
    0.38
    POSITIVE LOGITS
    瓢
    0.43
    芾
    0.41
    ड्डा
    0.40
     مكت
    0.40
    Padding
    0.40
    għ
    0.39
    Đ
    0.39
    Ba
    0.39
    BSData
    0.39
     පෙ
    0.39
    Activations Density 0.000%

    No Known Activations