© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 66987
    Prev
    Next
    INDEX
    Explanations

    specific types of carbon

    np_acts-logits-general · gemini-2.5-flash-lite

    carbon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     chamomile
    0.54
     glandular
    0.51
    qPCR
    0.50
    ("/{
    0.46
    🥰
    0.45
    댄
    0.45
     جغ
    0.45
    ズル
    0.44
     calyc
    0.44
     gerakan
    0.43
    POSITIVE LOGITS
     Carbon
    1.11
     carbon
    1.07
     कार्बन
    1.05
     الكربون
    1.01
    Carbon
    1.00
    炭
    0.98
    碳
    0.97
    carbon
    0.95
     carbono
    0.93
     CARBON
    0.91
    Activations Density 0.081%

    No Known Activations