© 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. 251332
    Prev
    Next
    INDEX
    Explanations

    businesses, software, and computing

    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
     или
    0.47
     ру
    0.42
     ឬ
    0.42
     หรือ
    0.41
     ಸುರ
    0.41
    othy
    0.39
    rug
    0.38
     rubles
    0.38
     largas
    0.38
     בק
    0.38
    POSITIVE LOGITS
    덫
    0.50
     metadata
    0.46
     PROBLE
    0.46
     shelved
    0.45
     emble
    0.43
    困
    0.43
     vítimas
    0.43
     Metadata
    0.43
     doubleheader
    0.43
     svoje
    0.42
    Activations Density 0.001%

    No Known Activations