© 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. 2313
    Prev
    Next
    INDEX
    Explanations

    unexpected events

    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
    ما
    1.55
    )"
    1.34
     시
    1.31
    )
    1.30
     동안
    1.28
     아마
    1.24
    ):
    1.20
     ordeal
    1.20
    나
    1.19
     [])
    1.18
    POSITIVE LOGITS
    teg
    1.59
    l
    1.56
    ן
    1.47
    clusion
    1.46
    ла
    1.45
    texto
    1.41
     Milit
    1.40
     Genes
    1.39
    teile
    1.39
    entlichen
    1.39
    Activations Density 0.010%

    No Known Activations