© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 151
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
     يعد
    0.84
     下
    0.83
     시
    0.78
     코로나
    0.78
     約
    0.75
     해당하는
    0.75
     山
    0.75
    Já
    0.75
     스마트
    0.75
     początku
    0.74
    POSITIVE LOGITS
     priors
    0.86
     adherents
    0.86
     speculations
    0.85
     upregulation
    0.83
     guardianship
    0.83
     jurors
    0.81
     alkaloids
    0.81
     worshippers
    0.81
     informants
    0.80
     sutures
    0.80
    Activations Density 0.000%

    No Known Activations