© 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-16K
    7. 9116
    Prev
    Next
    INDEX
    Explanations

    endings, bad endings)

    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_16k_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
    ㌔
    1.55
    ➥
    1.50
     γνω
    1.45
    事物
    1.42
     complejos
    1.41
     insectes
    1.39
     garantizar
    1.38
     salespeople
    1.38
     multiplicities
    1.37
     biofilms
    1.37
    POSITIVE LOGITS
    ل
    2.05
    f
    1.85
    اب
    1.82
    in
    1.79
                
    1.77
    ি
    1.73
                    
    1.67
        
    1.66
    et
    1.65
    ap
    1.63
    Activations Density 0.299%

    No Known Activations