© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76604
    Prev
    Next
    INDEX
    Explanations

    pass

    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
    take
    -1.02
     символи
    -0.90
     جانب
    -0.88
     JES
    -0.88
    .
    -0.87
     Nozzle
    -0.85
    两年
    -0.84
    を活用
    -0.84
    茕
    -0.84
    だからこそ
    -0.82
    POSITIVE LOGITS
     Pass
    1.31
     muster
    1.13
    Pass
    1.10
     Traditionally
    1.05
     PASS
    1.02
    photographe
    1.02
    ależy
    1.01
     Eigentümer
    1.00
    行政区
    0.96
    PASS
    0.96
    Activations Density 0.028%

    No Known Activations