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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7209
    Prev
    Next
    INDEX
    Explanations

    split or divide

    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_31_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
    Sleeping
    0.58
    幸运
    0.56
     nesting
    0.54
    SE
    0.53
     fortunate
    0.51
     Sleeping
    0.50
    ᠩ
    0.50
    SLE
    0.48
     lucky
    0.48
    }_{{\
    0.48
    POSITIVE LOGITS
     split
    2.05
    split
    2.00
     Split
    1.94
    Split
    1.87
     splitting
    1.84
     splits
    1.80
    splitted
    1.61
    splitting
    1.59
     Splits
    1.53
     splitter
    1.52
    Activations Density 0.347%

    No Known Activations