© 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. 92533
    Prev
    Next
    INDEX
    Explanations

    specific parcelcoastline or houselarge deductible plans

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

    Focusing, correlating, asking, defining

    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
     laatste
    0.51
    ษา
    0.46
     feest
    0.46
    ائل
    0.45
    kende
    0.45
    ydd
    0.45
    ارة
    0.44
    aal
    0.44
    k
    0.44
     geno
    0.43
    POSITIVE LOGITS
     enunci
    0.61
     encaps
    0.48
     Altitude
    0.47
     encouraging
    0.46
    ylmethylsulfanyl
    0.46
    วิว
    0.45
     unlike
    0.44
    วัง
    0.44
     advocating
    0.43
     TextInput
    0.43
    Activations Density 0.001%

    No Known Activations