© 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-262K
    7. 4994
    Prev
    Next
    INDEX
    Explanations

    array or method

    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
     জ
    1.08
     或
    1.06
    s
    1.04
     หรือ
    1.03
    ↵
    1.00
    ﺔ
    0.92
     پ
    0.91
     ว
    0.91
    Caso
    0.89
     ا
    0.87
    POSITIVE LOGITS
     constante
    0.89
    द्रोह
    0.89
     również
    0.84
     semua
    0.82
     bijna
    0.82
     magnific
    0.81
     alberga
    0.80
     continúa
    0.80
    其余
    0.80
     stderr
    0.79
    Activations Density 0.563%

    No Known Activations