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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102511
    Prev
    Next
    INDEX
    Explanations

    pairs and shares

    np_acts-logits-general · gemini-2.5-flash-lite

    bricks, blocks, rotating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     store
    0.55
     id
    0.53
    store
    0.52
    ↵↵↵↵
    0.51
     start
    0.49
     treaty
    0.48
     RTC
    0.48
    was
    0.47
    ↵↵↵
    0.47
     Store
    0.47
    POSITIVE LOGITS
    ᔪ
    0.62
     гульнявыя
    0.61
    ExternalTaskPojo
    0.58
    リーム
    0.55
    ꞎ
    0.55
    ड़ने
    0.55
    𝕝
    0.55
    ޏ
    0.54
    魟
    0.53
     мае
    0.52
    Activations Density 0.000%

    No Known Activations