© 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. 5723
    Prev
    Next
    INDEX
    Explanations

    the following

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

    explanation:**

    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
     Planning
    0.50
     Databases
    0.47
     PLANNING
    0.45
     진
    0.45
     Beverages
    0.44
     Activities
    0.43
    READ
    0.43
     HAVE
    0.43
     源
    0.42
    ences
    0.42
    POSITIVE LOGITS
     custod
    0.47
    fuse
    0.46
     shuttle
    0.45
     commits
    0.45
     ارب
    0.45
     princesa
    0.45
     سيدنا
    0.45
     sẽ
    0.43
     sería
    0.43
    でも
    0.43
    Activations Density 0.000%

    No Known Activations