© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6872
    Prev
    Next
    INDEX
    Explanations

    listing prior work

    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
     oiseaux
    0.61
     atrak
    0.61
     équip
    0.57
     مشتقه
    0.57
    肦
    0.57
     obec
    0.56
     sintered
    0.56
     variétés
    0.55
     sulphate
    0.55
     Ribe
    0.54
    POSITIVE LOGITS
    Also
    0.53
    this
    0.51
    Additionally
    0.51
    COPY
    0.49
    This
    0.48
    ↵
    0.48
    子
    0.48
    Project
    0.47
    a
    0.47
    COVID
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.