© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11046
    Prev
    Next
    INDEX
    Explanations

    medical topics and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     וא
    2.03
    ÇÃO
    1.95
     wonderland
    1.79
     mercenary
    1.75
     graphique
    1.73
                
    1.70
    তবে
    1.63
     indictment
    1.59
    岖
    1.59
    也
    1.58
    POSITIVE LOGITS
    nome
    2.36
    ب
    2.36
    nas
    2.30
    nar
    2.06
    nus
    2.05
    nr
    2.03
     ибо
    2.03
    nos
    2.02
     atteindre
    2.02
    ⚕
    2.02
    Activations Density 0.020%

    No Known Activations