© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91616
    Prev
    Next
    INDEX
    Explanations

    moneyguarantee

    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
    ㈜
    -0.88
    افظة
    -0.79
    霸王
    -0.76
     suffered
    -0.73
     colher
    -0.73
     suffer
    -0.72
    racist
    -0.70
    ではありません
    -0.69
    </th>
    -0.69
     sofrer
    -0.69
    POSITIVE LOGITS
     Money
    0.97
    ((((
    0.81
     MEN
    0.79
    (((
    0.78
     cents
    0.78
     нет
    0.77
    MAKE
    0.77
    𝐎
    0.75
    she
    0.75
    慣
    0.73
    Activations Density 0.022%

    No Known Activations