© 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. 1821
    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
     Things
    0.70
     importants
    0.70
    😀
    0.70
     বিবিসির
    0.70
    😕
    0.67
     Why
    0.67
    😧
    0.67
    Things
    0.66
    严重
    0.66
    😗
    0.66
    POSITIVE LOGITS
     transversal
    0.62
    同様
    0.59
    берём
    0.58
     (#
    0.57
     numeral
    0.57
    voud
    0.57
     reformer
    0.56
    導
    0.56
    łada
    0.56
     finisher
    0.55
    Activations Density 0.430%

    No Known Activations