© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17836
    Prev
    Next
    INDEX
    Explanations

    parameters and performance

    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
    лама
    0.47
    니까
    0.46
    를
    0.45
     그러니까
    0.45
     Бар
    0.44
    きちんと
    0.44
    Altri
    0.44
     То
    0.43
     EnglishChoose
    0.43
     stately
    0.43
    POSITIVE LOGITS
     संकेत
    0.45
     cedo
    0.43
     early
    0.43
     asap
    0.42
     l
    0.42
     claimed
    0.42
    images
    0.40
     aparent
    0.39
     for
    0.39
    assert
    0.39
    Activations Density 0.005%

    No Known Activations