© 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. 5358
    Prev
    Next
    INDEX
    Explanations

    Also, additional, sometimes

    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
    業界
    0.69
    owntown
    0.66
     સમગ્ર
    0.66
    🏭
    0.66
     समुद्रा
    0.65
     म्हणूनच
    0.64
    的には
    0.64
    Werk
    0.64
    全く
    0.63
    Ⴝ
    0.63
    POSITIVE LOGITS
     corticoster
    0.78
     corticosteroids
    0.68
     izin
    0.66
     cortisol
    0.61
     anticoagulant
    0.61
     emoji
    0.60
     acetylation
    0.60
     captcha
    0.60
     dizziness
    0.58
     pabbaj
    0.57
    Activations Density 0.729%

    No Known Activations