© 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. 76418
    Prev
    Next
    INDEX
    Explanations

    patent and IP rights

    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
     trademark
    -1.02
    PROOF
    -0.88
     Trademark
    -0.82
    ();*/
    -0.79
    专利
    -0.79
     pouvait
    -0.79
    ᕕ
    -0.76
    όμε
    -0.75
     Attribution
    -0.74
    AppConfig
    -0.74
    POSITIVE LOGITS
     rights
    1.11
     enforcement
    0.88
     valid
    0.84
     diritti
    0.83
     owned
    0.83
     validity
    0.83
     enforce
    0.81
     registrations
    0.81
     portfolio
    0.81
     assets
    0.79
    Activations Density 0.087%

    No Known Activations