© 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. 142660
    Prev
    Next
    INDEX
    Explanations

    host afterlife tour agreed analysis saving

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

    fruit, anime, PID, power, hungry

    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
    UPDATE
    0.54
    MSBuildTools
    0.47
     Geld
    0.46
     فهو
    0.45
    FileData
    0.44
    姓
    0.44
    ية
    0.43
    Gir
    0.43
     რომლებიც
    0.43
    P
    0.43
    POSITIVE LOGITS
    ushroom
    0.47
    மது
    0.47
     traduire
    0.45
    uation
    0.44
     brownish
    0.44
    হিন্দু
    0.44
     glimmer
    0.43
     soaked
    0.43
    থিত
    0.43
    soaked
    0.42
    Activations Density 0.000%

    No Known Activations