© 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. 100189
    Prev
    Next
    INDEX
    Explanations

    Ghanaian government and Akufo-Addo

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

    title: Text

    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
    cC
    0.44
     diffraction
    0.41
    icycl
    0.40
     Mate
    0.40
     Meadow
    0.40
    ྰ
    0.40
    莜
    0.40
    Mead
    0.39
    unca
    0.39
    Mate
    0.39
    POSITIVE LOGITS
    ->
    0.43
    霓
    0.43
     понимать
    0.39
     инде
    0.39
    нали
    0.38
     中央
    0.38
    сторон
    0.38
     esi
    0.37
    niger
    0.36
     そして
    0.36
    Activations Density 0.009%

    No Known Activations