© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3588
    Prev
    Next
    INDEX
    Explanations

    Antenna design validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    父亲
    4.81
     圖
    4.73
     женой
    4.68
     интервью
    4.64
     председа
    4.62
    地图
    4.61
     Великобритании
    4.61
    父親
    4.61
     комите
    4.59
     июле
    4.58
    POSITIVE LOGITS
    -
    -0.34
    ,
    -0.34
      
    -0.37
    1
    -0.53
    暄
    -0.55
    5
    -0.56
    3
    -0.59
    4
    -0.62
    2
    -0.63
    崧
    -0.63
    Activations Density 0.292%

    No Known Activations