© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82495
    Prev
    Next
    INDEX
    Explanations

    URLs and paths

    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
     even
    -1.09
     such
    -0.98
    里
    -0.84
     >
    -0.83
    )}_
    -0.82
     management
    -0.82
    >';
    -0.81
    に限
    -0.81
    女生
    -0.80
    德里
    -0.80
    POSITIVE LOGITS
    Recept
    1.00
    最近は
    0.98
     @$
    0.94
    この時期
    0.94
    おかげ
    0.90
     Atención
    0.88
     창
    0.87
     reas
    0.87
    Buon
    0.87
    Specifik
    0.87
    Activations Density 0.027%

    No Known Activations