© 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. 8050
    Prev
    Next
    INDEX
    Explanations

    history and science topics

    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
    mem
    0.54
     realities
    0.54
    reality
    0.54
    iz
    0.52
    }\}$.
    0.51
    ӳ
    0.47
    alors
    0.46
    érience
    0.46
    േ
    0.46
     dynamics
    0.46
    POSITIVE LOGITS
     विचार
    0.55
     slippers
    0.52
     lengthwise
    0.51
     utensils
    0.51
     shoes
    0.49
     pensiero
    0.49
     جاتے
    0.48
     brind
    0.48
     hank
    0.47
     mankind
    0.47
    Activations Density 0.014%

    No Known Activations