© 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-262K
    7. 40543
    Prev
    Next
    INDEX
    Explanations

    chlorophyll or mozzarella

    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
     Sudah
    1.36
     concernant
    1.23
    újt
    1.22
    are
    1.17
     couvrir
    1.17
    8
    1.16
     můžete
    1.15
     devant
    1.08
     Ketika
    1.07
    j
    1.07
    POSITIVE LOGITS
    ים
    1.40
    s
    1.38
     intentions
    1.29
    spapers
    1.28
     SNPs
    1.23
     lipoproteins
    1.22
    ы
    1.20
     footnotes
    1.18
     phonons
    1.17
     Yoruba
    1.16
    Activations Density 0.001%

    No Known Activations