© 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. 1948
    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
     glycolysis
    0.64
     concord
    0.63
     nucleons
    0.59
     concordance
    0.59
     perturbation
    0.57
     blockers
    0.56
    干
    0.54
    孬
    0.54
     aliqu
    0.53
     convergence
    0.53
    POSITIVE LOGITS
     Out
    0.61
    Out
    0.60
     ✓
    0.58
    Dire
    0.56
     Suits
    0.56
     !
    0.55
     Affected
    0.53
     Helped
    0.53
     !!
    0.53
     દી
    0.53
    Activations Density 0.000%

    No Known Activations