© 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. 22-GEMMASCOPE-RES-131K
    7. 72290
    Prev
    Next
    INDEX
    Explanations

    price, sale, reduction

    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
    FOOTNOTES
    -1.05
     vínculo
    -0.94
    mathrm
    -0.93
    jskiej
    -0.93
    աստ
    -0.92
     when
    -0.92
     Visite
    -0.91
    hibition
    -0.90
     a
    -0.89
    qs
    -0.89
    POSITIVE LOGITS
    ビア
    1.01
     orice
    0.97
    چرخ
    0.96
    immen
    0.95
    Any
    0.94
    因为
    0.94
    毕业
    0.93
    因為
    0.93
     pluie
    0.92
    Please
    0.90
    Activations Density 0.008%

    No Known Activations