© 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-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53733
    Prev
    Next
    INDEX
    Explanations

    palace"}, {"1": "city palace"}, {"1": "royal palace"}, {"1": "hofburg palace"}, {"1": "topkapı palace"}, {"0": "doge's palace"}This suggests the neuron is strongly associated with structures like "palace".TheTOKENS_AFTER_MAX_ACTIVATING_TOKEN list shows "Palace" following "cour".palace buildings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subm
    0.41
     lazım
    0.41
     മല
    0.40
     disulfide
    0.39
    担
    0.39
     biomedical
    0.39
     فلا
    0.38
     indigenous
    0.38
     McKinney
    0.38
     native
    0.38
    POSITIVE LOGITS
     جگ
    0.37
    StreetMap
    0.36
     ponctu
    0.35
     curator
    0.35
    fetched
    0.34
    Tales
    0.34
     стрельца
    0.34
    UREG
    0.34
    selectable
    0.33
     enlarg
    0.33
    Activations Density 0.032%

    No Known Activations