© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 43130
    Prev
    Next
    INDEX
    Explanations

    economic development

    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
    genomes
    0.84
    ق
    0.84
    qus
    0.84
    quirements
    0.82
    Journey
    0.82
    Autocomplete
    0.80
     isomorphisms
    0.80
     Alloys
    0.77
    quinazoline
    0.76
     कारणों
    0.75
    POSITIVE LOGITS
     Sonora
    0.83
    怿
    0.80
     fazem
    0.76
     Weierstrass
    0.73
    ਿਆਂ
    0.72
    ів
    0.70
     먼저
    0.70
    #%%
    0.69
    蜒
    0.69
    izing
    0.68
    Activations Density 0.000%

    No Known Activations