© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26506
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嫑
    -0.93
    锨
    -0.88
    轳
    -0.88
    描く
    -0.86
     montaż
    -0.85
    presented
    -0.82
    ってみた
    -0.82
     pleasure
    -0.82
    苤
    -0.82
     カラー
    -0.81
    POSITIVE LOGITS
     when
    1.06
     cuando
    1.02
    when
    0.99
    When
    0.96
     mengangg
    0.94
    czyć
    0.89
     their
    0.88
    paravant
    0.85
    Carreira
    0.84
     nearing
    0.84
    Activations Density 0.023%

    No Known Activations