© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 175769
    Prev
    Next
    INDEX
    Explanations

    favorite Artists

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

    slower speed or status

    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
     증가
    0.66
     nhiệm
    0.51
     miếng
    0.50
     नकली
    0.50
     transpose
    0.49
     ውጤ
    0.48
     层
    0.48
     клет
    0.47
     ㅜ
    0.46
     counterfe
    0.46
    POSITIVE LOGITS
    лом
    0.52
    Anda
    0.51
    You
    0.50
    Your
    0.50
    leading
    0.49
    й
    0.48
    全国
    0.48
    ause
    0.47
    ULL
    0.47
    зе
    0.47
    Activations Density 0.000%

    No Known Activations