© 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. 13921
    Prev
    Next
    INDEX
    Explanations

    There are / there is

    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
     Уен
    0.64
    Core
    0.60
    kel
    0.59
    CU
    0.59
    浱
    0.58
    cw
    0.58
    CW
    0.58
    core
    0.56
    dose
    0.55
    laf
    0.55
    POSITIVE LOGITS
     `/
    0.73
     `%
    0.63
     существуют
    0.61
     exist
    0.59
     exists
    0.59
     `=
    0.57
     `$
    0.57
     contamination
    0.55
    一条
    0.55
     possibility
    0.55
    Activations Density 0.053%

    No Known Activations