© 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. 192067
    Prev
    Next
    INDEX
    Explanations

    board informed

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

    items as

    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
    它
    0.45
    SOFT
    0.45
    ਠ
    0.44
    ))],
    0.44
    빵
    0.43
    軟
    0.43
     일정
    0.43
    儲
    0.43
    嬌
    0.42
    6
    0.42
    POSITIVE LOGITS
     illustrate
    0.48
    लेश्वर
    0.47
    迨
    0.47
    ഔ
    0.47
     मल्टीप्लिकेशन
    0.46
    ForRule
    0.46
    𒄩
    0.45
     partite
    0.45
     endorse
    0.45
    BeforeText
    0.45
    Activations Density 0.001%

    No Known Activations