Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19437
    Prev
    Next
    INDEX
    Explanations

    project identifiers

    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
    给自己
    0.41
    让自己
    0.40
    実施
    0.40
    讓
    0.40
     anatomic
    0.38
    礬
    0.38
    }=-\
    0.37
     প্রস্তুত
    0.37
    itabbo
    0.37
    ēng
    0.36
    POSITIVE LOGITS
     Candy
    0.50
     N
    0.49
     Z
    0.47
     Apache
    0.47
     Learning
    0.45
     Lego
    0.45
     Dynamic
    0.44
     Hadoop
    0.44
     Video
    0.44
     Collaborative
    0.44
    Activations Density 0.001%

    No Known Activations