© 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. 8629
    Prev
    Next
    INDEX
    Explanations

    in the sense

    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
     necessariamente
    0.66
     nécessairement
    0.63
     necessarily
    0.57
     تھیں۔
    0.52
    %。
    0.52
     necesariamente
    0.51
     कोणते
    0.49
    Commun
    0.48
     로
    0.48
    萝
    0.48
    POSITIVE LOGITS
     sense
    0.91
     strictest
    0.81
     Sense
    0.79
     senses
    0.78
     sentido
    0.75
     true
    0.73
     strict
    0.71
    sense
    0.69
     senso
    0.68
     broad
    0.65
    Activations Density 0.143%

    No Known Activations