© 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. 12555
    Prev
    Next
    INDEX
    Explanations

    references, phrases, participate, married, format

    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
     Puedes
    0.89
     Toutes
    0.85
     pouvaient
    0.85
    لاميذ
    0.82
    🆙
    0.82
    予想
    0.81
    Kya
    0.79
    帐户
    0.79
    zugs
    0.79
     avaient
    0.78
    POSITIVE LOGITS
     styr
    0.73
    OLA
    0.72
    Boston
    0.68
    friction
    0.67
    𝙛
    0.67
    특별시
    0.66
     friction
    0.65
    한강
    0.64
     Hawthorne
    0.63
     VL
    0.63
    Activations Density 0.000%

    No Known Activations