© 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. 252038
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    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
     問
    0.48
     mitt
    0.45
     nett
    0.44
     감소
    0.43
     മേഖ
    0.43
    最短
    0.43
    ঠাৎ
    0.42
    brokers
    0.42
    ◡
    0.40
     কেন্দ্র
    0.40
    POSITIVE LOGITS
    í
    0.50
    มี
    0.48
    ิง
    0.47
    iiii
    0.47
     aile
    0.47
    ټ
    0.45
    sequent
    0.44
    慈
    0.44
    iß
    0.43
     équipé
    0.43
    Activations Density 0.000%

    No Known Activations