© 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. 20528
    Prev
    Next
    INDEX
    Explanations

    multi-language recognition

    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
     etwa
    0.43
     ausp
    0.35
     watershed
    0.34
     amidst
    0.34
     poise
    0.34
     whol
    0.33
     auparavant
    0.33
    3
    0.33
     tadi
    0.33
     Instead
    0.32
    POSITIVE LOGITS
    机场
    0.51
     మరియు
    0.50
    的其他
    0.49
    ándole
    0.49
    房价
    0.48
    các
    0.48
    🄰
    0.47
     সেরা
    0.46
     ఇతర
    0.46
     של
    0.46
    Activations Density 0.011%

    No Known Activations