© 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. 1708
    Prev
    Next
    INDEX
    Explanations

    keeping the core meaning

    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
     HUGE
    0.78
    0.70
     VERY
    0.68
    !!!
    0.66
     +
    0.65
     엄청
    0.65
     BUT
    0.63
     almost
    0.63
     scream
    0.63
     O
    0.62
    POSITIVE LOGITS
     adlı
    0.73
     offenbar
    0.72
     yakni
    0.71
     noteworthy
    0.70
     furnishings
    0.69
     selaku
    0.69
     වෙත
    0.69
     உள்ளிட்ட
    0.69
     soltanto
    0.68
     गौरतलब
    0.68
    Activations Density 1.677%

    No Known Activations