© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2620
    Prev
    Next
    INDEX
    Explanations

    **numerical values and specific words**

    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
     отрима
    0.91
    ال
    0.88
    ه
    0.86
     volutpat
    0.84
     Seperti
    0.78
     معظم
    0.78
     정
    0.75
    i
    0.75
    부터
    0.74
     나서
    0.74
    POSITIVE LOGITS
    ತಿ
    0.90
    ены
    0.86
    ิล
    0.85
    trivia
    0.83
    ילו
    0.82
    IEN
    0.82
    ensity
    0.81
    ্রো
    0.81
    synt
    0.79
    лены
    0.78
    Activations Density 0.000%

    No Known Activations