© 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. 15317
    Prev
    Next
    INDEX
    Explanations

    tables with | and +

    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
    сть
    2.33
     videog
    2.14
    ี
    1.98
    ства
    1.92
     Dynkin
    1.92
     scr
    1.91
     fashioned
    1.84
     scour
    1.84
     beset
    1.80
    ות
    1.80
    POSITIVE LOGITS
    ル
    2.66
    ১
    2.34
    ک
    2.22
    nije
    2.19
    ał
    2.19
    ง
    2.17
    ك
    2.16
    í
    2.14
    ח
    2.09
     indicó
    2.03
    Activations Density 0.053%

    No Known Activations