© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27841
    Prev
    Next
    INDEX
    Explanations

    prepared almost

    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
    Completion
    -1.05
    IVATION
    -1.01
    lant
    -1.00
     τὴν
    -0.96
    idom
    -0.94
     sposób
    -0.90
    ΠΕ
    -0.89
    cesso
    -0.85
    isseurs
    -0.84
     Paix
    -0.84
    POSITIVE LOGITS
    ຣ
    1.03
     within
    0.90
    áles
    0.90
    Brend
    0.82
    그리고
    0.81
    rég
    0.79
     применять
    0.79
     immunization
    0.78
    constexpr
    0.77
    ִּ
    0.77
    Activations Density 0.096%

    No Known Activations