© 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. 22-GEMMASCOPE-RES-131K
    7. 25031
    Prev
    Next
    INDEX
    Explanations

    fees, demands, or insurance

    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
    Negative Logits
    jarati
    -0.88
    Bbb
    -0.83
    За
    -0.82
    iniques
    -0.82
    يم
    -0.81
    ISupport
    -0.81
    От
    -0.80
     sintomas
    -0.79
     теоре
    -0.79
    nello
    -0.79
    POSITIVE LOGITS
     demands
    1.14
     demanded
    1.08
    提出的
    1.03
     rescate
    0.96
     الماضي
    0.94
    ‌آم
    0.93
    ffiche
    0.92
     bestaande
    0.91
    urances
    0.91
    ceptable
    0.89
    Activations Density 0.047%

    No Known Activations