© 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. 996
    Prev
    Next
    INDEX
    Explanations

    comparison operators

    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
     туда
    0.59
    *;
    0.53
     spät
    0.52
    /;
    0.52
     använda
    0.51
     మొత్త
    0.50
    ونک
    0.49
     wprowad
    0.49
    ]$;
    0.49
    하지만
    0.49
    POSITIVE LOGITS
     ==
    2.84
     !=
    2.36
    ==
    2.33
    =="
    2.02
     >=
    1.94
    !=
    1.91
     ===
    1.90
     <=
    1.82
    ()==
    1.80
    =='
    1.80
    Activations Density 0.324%

    No Known Activations