© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56820
    Prev
    Next
    INDEX
    Explanations

    amount, amounts, tune

    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
    Negative Logits
     that
    -0.79
     pricing
    -0.77
    ご理解
    -0.73
     across
    -0.72
     considering
    -0.71
     likely
    -0.70
    ليات
    -0.69
    ないです
    -0.67
     reservations
    -0.67
    ona
    -0.66
    POSITIVE LOGITS
     amount
    2.66
    amount
    2.38
     tune
    2.16
    Amount
    2.14
     Amount
    2.11
     amounts
    2.06
     AMOUNT
    2.03
     amounting
    2.00
     amounted
    1.79
    AMOUNT
    1.77
    Activations Density 0.028%

    No Known Activations