© 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. 229492
    Prev
    Next
    INDEX
    Explanations

    you accept

    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
    នៃ
    0.45
    ొప్పి
    0.45
     海
    0.44
     Geographical
    0.44
     الحكومة
    0.44
     Destination
    0.43
     Balliye
    0.43
    nameSort
    0.43
     Beds
    0.42
     Government
    0.42
    POSITIVE LOGITS
    া
    0.54
     autonomously
    0.49
    деа
    0.48
     डों
    0.48
     використо
    0.48
    ва
    0.47
    ایی
    0.46
    eve
    0.46
    ница
    0.44
    IBM
    0.44
    Activations Density 0.001%

    No Known Activations