© 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. 3391
    Prev
    Next
    INDEX
    Explanations

    break down

    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
     chẳng
    2.27
     eget
    2.09
     불구하고
    2.08
    ran
    2.03
    ない
    1.96
    ς
    1.92
    hh
    1.91
    ري
    1.90
     nigris
    1.90
    醐
    1.86
    POSITIVE LOGITS
    et
    1.84
     Règles
    1.81
    şehir
    1.78
    idcoin
    1.59
    emos
    1.53
    på
    1.52
     kalimat
    1.52
     Whole
    1.52
     रिश्ता
    1.49
     المج
    1.48
    Activations Density 0.357%

    No Known Activations