© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 757
    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_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
    чному
    0.44
    createNew
    0.43
    embalikan
    0.42
    éristique
    0.41
    ッと
    0.40
    Су
    0.40
    敎
    0.40
    눠
    0.39
    ッテリー
    0.39
    iminary
    0.39
    POSITIVE LOGITS
    speople
    0.51
     portrayed
    0.50
     toppers
    0.49
    referred
    0.48
     depicted
    0.47
     neoplasms
    0.47
    bergs
    0.47
     referred
    0.46
     undergoes
    0.46
     excreted
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.