© 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. 15843
    Prev
    Next
    INDEX
    Explanations

    underscore character

    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
     trocar
    0.56
    Église
    0.55
     eroding
    0.53
    bertson
    0.53
    परेटर
    0.52
     zajed
    0.51
    接
    0.50
    試合
    0.50
     jod
    0.50
     pesticide
    0.49
    POSITIVE LOGITS
     bold
    1.45
    強調
    1.43
    Bold
    1.41
    bold
    1.38
     emphasised
    1.34
    emphas
    1.32
    强调
    1.30
     Bold
    1.30
     emphasise
    1.28
     emphasized
    1.27
    Activations Density 0.306%

    No Known Activations