© 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. 388
    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
    藕
    0.93
    ২১
    0.82
    ্লিকেশন
    0.82
     året
    0.76
    тын
    0.76
     alkene
    0.75
    」、
    0.75
    碘
    0.75
     машиналарын
    0.74
    拿
    0.74
    POSITIVE LOGITS
     ومرحبا
    0.90
    unz
    0.83
    wa
    0.82
    ia
    0.81
    Carta
    0.80
    ма
    0.80
     arrêté
    0.80
    ubin
    0.79
    jillo
    0.79
    ar
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.