© 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. 22-GEMMASCOPE-RES-131K
    7. 34769
    Prev
    Next
    INDEX
    Explanations

    affirmation or correctness

    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
     and
    -0.85
    replication
    -0.84
    ǿ
    -0.83
     series
    -0.81
     desapar
    -0.79
    comparison
    -0.78
    なみ
    -0.75
    完
    -0.74
     Clearing
    -0.73
     compiler
    -0.73
    POSITIVE LOGITS
     correct
    1.55
     части
    1.35
     đúng
    1.33
    確かに
    1.27
     Correct
    1.21
     čás
    1.19
     partially
    1.19
     czę
    1.16
    части
    1.16
    Correct
    1.14
    Activations Density 0.036%

    No Known Activations