© 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. 12669
    Prev
    Next
    INDEX
    Explanations

    testing

    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
     cercanos
    1.66
     fundamentos
    1.62
    Ά
    1.61
     enfermos
    1.56
     Respondents
    1.55
     എസ്
    1.53
     novedades
    1.52
     ugljik
    1.50
    
    1.48
     residuos
    1.47
    POSITIVE LOGITS
    م
    2.38
    ش
    1.98
    ا
    1.81
    ق
    1.79
    iy
    1.73
    ying
    1.65
    ey
    1.63
    imed
    1.54
    ap
    1.51
    t
    1.51
    Activations Density 0.022%

    No Known Activations