© 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. 15035
    Prev
    Next
    INDEX
    Explanations

    concentration vs. time

    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
     […]
    0.59
    ெமி
    0.47
    […]
    0.44
     For
    0.44
    ramble
    0.44
     对于
    0.43
    In
    0.43
     Бу
    0.43
     alot
    0.43
    For
    0.42
    POSITIVE LOGITS
     derogatory
    0.44
     stockbild
    0.43
     फैन्स
    0.42
    🔅
    0.42
    ো
    0.41
     makeshift
    0.41
     należy
    0.40
     recounting
    0.40
     murmured
    0.40
     conspiracy
    0.40
    Activations Density 0.574%

    No Known Activations