© 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. 91394
    Prev
    Next
    INDEX
    Explanations

    financialtransactionscollusioncommission

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

    purpose or function

    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
     Trouble
    0.50
    adigan
    0.49
    ]$,
    0.48
     ಹೊಂದ
    0.46
     basi
    0.45
    left
    0.44
     well
    0.43
    oldown
    0.43
     மாய
    0.43
    unez
    0.43
    POSITIVE LOGITS
    мп
    0.52
    сё
    0.51
    ТУ
    0.50
    कक्ष
    0.48
     алфа
    0.48
     asociaciones
    0.47
    ෘ
    0.47
    вед
    0.46
     blí
    0.46
     porcel
    0.45
    Activations Density 0.001%

    No Known Activations