© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71960
    Prev
    Next
    INDEX
    Explanations

    items, target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    ie
    0.56
    regated
    0.50
    il
    0.49
     kontek
    0.49
    sley
    0.48
    ’;
    0.48
    rophes
    0.48
    ět
    0.48
     ఉన్నారు
    0.47
    ih
    0.46
    POSITIVE LOGITS
     MTT
    0.48
    マルチ
    0.47
    த்துவ
    0.46
    滀
    0.45
    センター
    0.43
     BH
    0.42
    法
    0.41
     PES
    0.40
     کان
    0.40
    込み
    0.40
    Activations Density 0.006%

    No Known Activations