© 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. 99961
    Prev
    Next
    INDEX
    Explanations

    explaining with key takeaways

    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
     США
    0.50
     tokenId
    0.50
    вают
    0.48
    টসঅ্যাপ
    0.48
     tokenizer
    0.48
     레
    0.47
     То
    0.46
     탱크
    0.46
     toluene
    0.45
     zásobníku
    0.45
    POSITIVE LOGITS
    on
    0.54
    of
    0.46
    ony
    0.44
    ob
    0.43
    by
    0.42
    at
    0.41
     occupied
    0.40
    recogn
    0.40
    ter
    0.40
    redis
    0.39
    Activations Density 0.003%

    No Known Activations