© 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. 197216
    Prev
    Next
    INDEX
    Explanations

    investigator, operating system

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

    nutty beverages

    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
    SRPI
    0.55
    钝
    0.51
    arquía
    0.50
    ératures
    0.49
    闲
    0.48
    лин
    0.48
    емо
    0.47
    图形
    0.47
    サリー
    0.46
    müş
    0.46
    POSITIVE LOGITS
     :
    0.52
     KI
    0.50
     mellan
    0.50
     between
    0.49
     boiled
    0.49
     delicious
    0.47
     revamped
    0.47
     KU
    0.47
     wrote
    0.47
     hicieron
    0.46
    Activations Density 0.000%

    No Known Activations