© 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. 170323
    Prev
    Next
    INDEX
    Explanations

    thank you for your support

    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
     入っ
    0.50
    idiendo
    0.49
    篑
    0.48
    ণ্ডিত
    0.48
    HTree
    0.48
    जारत
    0.47
     longiore
    0.47
    ოლოდ
    0.46
    стом
    0.46
    +|\
    0.46
    POSITIVE LOGITS
     international
    0.53
     International
    0.51
    -
    0.51
     European
    0.50
     Russian
    0.50
     M
    0.49
    ,
    0.48
     has
    0.47
     Music
    0.47
     food
    0.46
    Activations Density 0.010%

    No Known Activations