© 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. 1132
    Prev
    Next
    INDEX
    Explanations

    sunshine and rainbows

    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
     (
    1.99
    （
    1.46
    (
    1.28
     ("
    1.27
     (!
    1.27
     এরূপ
    1.17
    /
    1.16
     (\"
    1.13
     हेतु
    1.10
     (~
    1.10
    POSITIVE LOGITS
    っていう
    1.42
     really
    1.39
     ähm
    1.34
     yeah
    1.29
     vraiment
    1.27
     น่ะ
    1.25
     kinda
    1.24
     Yeah
    1.23
     කියලා
    1.23
    이니까
    1.21
    Activations Density 0.365%

    No Known Activations