© 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. 61980
    Prev
    Next
    INDEX
    Explanations

    trends, growth, and changes

    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
    矫
    0.46
    实现
    0.44
    技术的
    0.44
    引入
    0.43
    机器人
    0.43
     wymaga
    0.43
    实践
    0.42
     transform
    0.42
     realizacji
    0.42
     transformative
    0.41
    POSITIVE LOGITS
    ナソニック
    0.47
    ఒ
    0.41
    መስ
    0.39
     น่ะ
    0.38
    +,
    0.38
    горе
    0.38
     rhyth
    0.38
     એક
    0.38
     թ
    0.38
     dilapidated
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.