© 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. 34-GEMMASCOPE-RES-131K
    7. 117151
    Prev
    Next
    INDEX
    Explanations

    Andrew followed by surname

    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_34/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
     モード
    -0.91
     評価
    -0.91
     also
    -0.91
     happily
    -0.87
     therefore
    -0.87
    จึง
    -0.84
     thus
    -0.81
    は以下の
    -0.80
    حاب
    -0.80
     reduced
    -0.79
    POSITIVE LOGITS
     Warhol
    1.11
     memahami
    1.01
     pytania
    0.97
     Sistema
    0.95
    睃
    0.93
    $--
    0.92
     positivo
    0.92
     potrebné
    0.92
    Andy
    0.90
     ác
    0.90
    Activations Density 0.009%

    No Known Activations