© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 147433
    Prev
    Next
    INDEX
    Explanations

    over the skies

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

    contrasting limitations

    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
    Negative Logits
     er
    0.52
     es
    0.50
     asymmetry
    0.49
     beat
    0.49
    :
    0.48
     le
    0.47
     substantive
    0.47
    warts
    0.47
     decency
    0.46
     ist
    0.46
    POSITIVE LOGITS
    ח
    0.49
     পাকিস্ত
    0.49
     लगाकर
    0.48
    राई
    0.48
     मारकर
    0.46
     އަ
    0.46
    ர்
    0.44
     findAll
    0.44
     ఆది
    0.44
     定义
    0.43
    Activations Density 0.001%

    No Known Activations