© 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. 196320
    Prev
    Next
    INDEX
    Explanations

    finance minister

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

    binary outcomes, on off

    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
     elev
    0.49
     baad
    0.49
     Saccharomyces
    0.48
     işlem
    0.48
     lluv
    0.47
    asambhavam
    0.46
     uur
    0.46
     ]),
    0.46
    जैसे
    0.45
     alınd
    0.45
    POSITIVE LOGITS
     Symphony
    0.44
     Notch
    0.43
    電池
    0.42
     Highways
    0.41
    ws
    0.41
    ന്ത്
    0.40
     explicitly
    0.40
     मिलेगी
    0.39
     pra
    0.39
     politische
    0.39
    Activations Density 0.001%

    No Known Activations