© 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. 69188
    Prev
    Next
    INDEX
    Explanations

    instructions or required actions

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

    technical and abstract concepts

    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
     север
    0.51
    価格
    0.50
    ੇ
    0.49
    ヨーロッパ
    0.49
     esperan
    0.48
    タ
    0.47
    ｽ
    0.47
    southern
    0.45
     городе
    0.45
    tahun
    0.45
    POSITIVE LOGITS
     =
    0.49
     kidnapping
    0.49
     všechny
    0.48
     control
    0.47
     malfunctioning
    0.46
     controls
    0.46
    必须
    0.46
     নিয়ন্ত্রণ
    0.46
     transduction
    0.45
     cells
    0.45
    Activations Density 0.002%

    No Known Activations