© 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. 37335
    Prev
    Next
    INDEX
    Explanations

    fictional businesses, nations, or people

    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
    son
    1.23
    𝐨
    1.09
    tive
    1.07
    eis
    1.05
    ्स
    1.04
    tır
    1.03
    tail
    1.02
    梠
    1.02
    יא
    1.02
    Ќ
    1.01
    POSITIVE LOGITS
     lieutenant
    0.86
    目的是
    0.86
    ம்
    0.82
    ান
    0.81
     wept
    0.80
    一度
    0.80
     woe
    0.79
    म्
    0.79
    合物
    0.79
     overpower
    0.79
    Activations Density 0.004%

    No Known Activations