© 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. 40-GEMMASCOPE-2-RES-262K
    7. 21210
    Prev
    Next
    INDEX
    Explanations

    :// www

    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_40_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
    ăţ
    0.40
    dataset
    0.40
     अदिति
    0.38
     பா
    0.38
     कुसुम
    0.37
    dri
    0.36
    ţin
    0.36
    >`;
    0.36
    ‴
    0.36
    definitions
    0.35
    POSITIVE LOGITS
    মার
    0.45
    www
    0.45
     www
    0.44
    吧
    0.38
    呀
    0.38
    Tahoma
    0.37
     Yah
    0.36
     समार
    0.35
     Ahu
    0.35
     Jamaica
    0.34
    Activations Density 0.000%

    No Known Activations