© 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. 107276
    Prev
    Next
    INDEX
    Explanations

    forms of to be followed by action

    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
    bagian
    -0.89
     diskusi
    -0.84
    瘆
    -0.81
    colorPrimary
    -0.78
     desplie
    -0.78
    ванні
    -0.77
     гр
    -0.77
     waged
    -0.77
     montón
    -0.77
     sabid
    -0.77
    POSITIVE LOGITS
     gaz
    0.81
     ear
    0.79
     ring
    0.79
     handball
    0.77
     ло
    0.77
     Handball
    0.75
    byter
    0.75
    itic
    0.74
     rubber
    0.74
    TX
    0.74
    Activations Density 0.074%

    No Known Activations