© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1568
    Prev
    Next
    INDEX
    Explanations

    calculating and processing data

    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
    ImageAsset
    0.64
    CipherText
    0.61
    Browsable
    0.58
    Installing
    0.57
    Cuál
    0.57
     khô
    0.56
     thoại
    0.55
    ៣
    0.54
     abiert
    0.54
     nhấn
    0.54
    POSITIVE LOGITS
     calculation
    1.39
     calculate
    1.36
     calculations
    1.33
    计算
    1.32
     calculated
    1.30
     processed
    1.27
     processing
    1.24
     recalculated
    1.23
     computations
    1.23
     calculating
    1.22
    Activations Density 1.443%

    No Known Activations