© 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. 85613
    Prev
    Next
    INDEX
    Explanations

    post section

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

    describing or customizing entities

    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
     meriye
    0.65
     definiciones
    0.59
     Augustin
    0.52
     vadati
    0.51
     индек
    0.49
     ITU
    0.49
     patitth
    0.48
    㕫
    0.48
     agacch
    0.48
    讫
    0.47
    POSITIVE LOGITS
    ι
    0.46
    multiple
    0.45
    attended
    0.44
     as
    0.43
    Multiple
    0.42
    εσ
    0.42
     पेंट
    0.42
    outdoor
    0.42
    administered
    0.42
     कामगिरी
    0.42
    Activations Density 0.001%

    No Known Activations