© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 281
    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
    but
    0.51
    But
    0.48
    Alright
    0.46
    Maybe
    0.46
    Kalau
    0.44
    ？
    0.44
    And
    0.44
    h
    0.43
    if
    0.42
    sh
    0.42
    POSITIVE LOGITS
     Additionally
    0.85
     These
    0.82
     Importantly
    0.76
     This
    0.69
     इसमें
    0.68
     Notably
    0.68
     Emphasis
    0.67
     Furthermore
    0.66
     これらの
    0.66
     Includes
    0.65
    Activations Density 4.251%

    No Known Activations