© 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. 128534
    Prev
    Next
    INDEX
    Explanations

    academy of [field]

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

    institutes and academies

    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
    or
    0.37
     Moran
    0.37
    か
    0.36
     ख्
    0.35
     व
    0.35
    णु
    0.35
    context
    0.35
    ি
    0.35
     gezegd
    0.34
    awt
    0.34
    POSITIVE LOGITS
     footballers
    0.45
     plumbers
    0.40
     für
    0.39
     Engineers
    0.38
     täht
    0.36
     پورے
    0.36
     চিকিৎসক
    0.36
     nutric
    0.36
     disponibilités
    0.36
     athletes
    0.35
    Activations Density 0.030%

    No Known Activations