© 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. 42155
    Prev
    Next
    INDEX
    Explanations

    resource files and layouts

    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
    s
    1.49
     enrichment
    0.81
     C
    0.81
     enriching
    0.79
     reforestation
    0.79
     R
    0.77
     outskirts
    0.77
    sides
    0.76
    ோ
    0.75
     orchards
    0.73
    POSITIVE LOGITS
    gaben
    1.07
     लिए
    1.06
    ências
    1.06
    setImageResource
    1.05
    ет
    1.05
    paintbrush
    1.04
    creens
    1.03
    oplayer
    1.02
     Маке
    1.02
     debajo
    1.01
    Activations Density 0.004%

    No Known Activations