© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6047
    Prev
    Next
    INDEX
    Explanations

    This neuron activates strongly on unusually rare or low‐frequency words in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     u
    0.86
     usu
    0.75
     Como
    0.74
     bevor
    0.73
    ING
    0.72
     hw
    0.71
     zakład
    0.71
     tocar
    0.70
    ャ
    0.70
     zak
    0.70
    POSITIVE LOGITS
    antibodies
    0.77
    them
    0.77
    intersects
    0.76
    cognitive
    0.75
    calories
    0.75
    footnotesize
    0.75
     horsepower
    0.73
     intérêts
    0.73
    gates
    0.73
    stitch
    0.73
    Activations Density 0.000%

    No Known Activations