© 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. 221385
    Prev
    Next
    INDEX
    Explanations

    inducing / induced

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

    specific words or constructs

    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
    でしたが
    0.52
    しましたが
    0.51
    だったので
    0.48
    したので
    0.45
    いますが
    0.44
     tagReport
    0.43
    zmdi
    0.43
    ┗
    0.41
    ские
    0.41
     нашли
    0.40
    POSITIVE LOGITS
    γκα
    0.50
     inducing
    0.48
     leveraged
    0.47
     sparing
    0.46
     Coelho
    0.46
     якості
    0.46
     induced
    0.46
     Induced
    0.46
    غ
    0.45
     उत्पाद
    0.45
    Activations Density 0.003%

    No Known Activations