© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1361
    Prev
    Next
    INDEX
    Explanations

    The neuron flags unusually rare or low‐frequency tokens (i.e. uncommon words or names).

    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_24_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
    ที่จะ
    0.89
     bele
    0.76
    k
    0.75
     Antes
    0.71
    脷
    0.70
    ܠܐ
    0.69
    nyk
    0.69
    UE
    0.68
    YAML
    0.68
    nem
    0.68
    POSITIVE LOGITS
    逦
    0.78
    anwhile
    0.75
    ゾ
    0.70
    ває
    0.70
     coinciding
    0.69
    триму
    0.68
    ారు
    0.68
     hairline
    0.68
    oretically
    0.68
    但是
    0.67
    Activations Density 0.020%

    No Known Activations