© 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. 206879
    Prev
    Next
    INDEX
    Explanations

    guesthouse, lakes, take

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

    someone might

    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
     მო
    0.50
     가지
    0.46
     Pann
    0.46
    არის
    0.46
    恚
    0.46
     BCCI
    0.46
     वि
    0.45
     δια
    0.45
     объяв
    0.45
     არ
    0.45
    POSITIVE LOGITS
    Highlights
    0.54
     adolescente
    0.47
    Many
    0.46
    Students
    0.46
    Sh
    0.45
    ------------
    0.45
    يت
    0.44
    في
    0.44
    Chinese
    0.44
    AN
    0.44
    Activations Density 0.001%

    No Known Activations