© 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. 34904
    Prev
    Next
    INDEX
    Explanations

    string manipulation and encoding

    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
    Deposit
    -0.85
    posited
    -0.79
     DEPOSIT
    -0.77
     deposited
    -0.75
    чно
    -0.75
    deposit
    -0.75
    otella
    -0.74
    明顯
    -0.71
     parody
    -0.71
     розвитку
    -0.70
    POSITIVE LOGITS
     url
    2.06
    url
    1.80
     html
    1.62
     strips
    1.40
    html
    1.30
     URL
    1.25
     str
    1.17
     trim
    1.16
     strip
    1.14
    Url
    1.13
    Activations Density 0.032%

    No Known Activations