Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 1209
    Prev
    Next
    INDEX
    Explanations

    Month (May - June)

    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
    IZED
    1.52
    하여
    1.46
    Пу
    1.46
    赔
    1.46
    Muc
    1.45
    য়াত
    1.43
    YPE
    1.38
    不一样
    1.38
    INEN
    1.35
     tecnici
    1.34
    POSITIVE LOGITS
    and
    2.02
    as
    1.66
    able
    1.59
    
    1.52
    いない
    1.50
    it
    1.48
    ס
    1.46
     agus
    1.44
     professionnelle
    1.41
     vais
    1.41
    Activations Density 0.000%

    No Known Activations