© 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. 2224
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     relaxation
    0.69
     quaint
    0.65
     innovation
    0.63
     homology
    0.62
     :-)
    0.61
     ergonomic
    0.61
     relaxing
    0.61
     ergonom
    0.61
     sampling
    0.60
     citizens
    0.59
    POSITIVE LOGITS
     betrayal
    1.39
     hurtful
    1.39
     heartbreak
    1.35
     hurt
    1.23
     heartache
    1.22
     Feelings
    1.19
     betrayed
    1.16
     feelings
    1.16
    💔
    1.16
     hurts
    1.12
    Activations Density 0.554%

    No Known Activations