© 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-16K
    7. 12332
    Prev
    Next
    INDEX
    Explanations

    first word in other languages

    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_16k_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
    了一个
    1.71
    ไม่ใช่
    1.70
    1.69
    써
    1.69
    ции
    1.67
     añad
    1.62
     pasó
    1.61
     risque
    1.60
     requisition
    1.56
    ])).
    1.55
    POSITIVE LOGITS
    it
    2.63
    ou
    2.58
    am
    2.38
    ac
    2.25
    т
    2.20
    ي
    2.17
    at
    2.16
    ча
    2.11
    ки
    2.06
    us
    2.05
    Activations Density 0.049%

    No Known Activations