© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8405
    Prev
    Next
    INDEX
    Explanations

    essays and academic topics

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     อย่าง
    0.52
    It
    0.51
    This
    0.50
    They
    0.50
    That
    0.49
    拂
    0.49
    These
    0.49
     Affairs
    0.48
    “
    0.48
     They
    0.48
    POSITIVE LOGITS
     dissertation
    0.82
     essay
    0.70
     coursework
    0.68
     essays
    0.67
     escritores
    0.67
     argumentative
    0.66
     thesis
    0.63
     escrever
    0.62
     competencias
    0.61
     profesores
    0.59
    Activations Density 0.071%

    No Known Activations