© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9811
    Prev
    Next
    INDEX
    Explanations

    form or analyze

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on longer, content-heavy or low-frequency tokens (i.e. longer, specialized vocabulary words).

    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
    0.89
    :
    0.77
     Grade
    0.75
     site
    0.74
     Identify
    0.72
     filed
    0.72
     appropriate
    0.71
     fixe
    0.71
     Opens
    0.70
    fa
    0.70
    POSITIVE LOGITS
    Paciente
    0.95
    
    0.93
    Czechoslovakia
    0.92
    
    0.89
    Sunset
    0.88
    Belarus
    0.86
    Patients
    0.84
    💩
    0.84
    IGA
    0.84
    
    0.84
    Activations Density 0.000%

    No Known Activations