© 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. 45210
    Prev
    Next
    INDEX
    Explanations

    information is available

    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
    DIPSETTING
    -0.90
    ximately
    -0.85
    Földrajzportál
    -0.82
    Predecesor
    -0.82
     possibles
    -0.81
     dilakukan
    -0.78
    Done
    -0.78
    执行
    -0.77
    üht
    -0.77
    дор
    -0.77
    POSITIVE LOGITS
     gathered
    1.58
     available
    1.36
     collected
    1.31
     accessible
    1.24
    gathered
    1.23
     obtained
    1.19
     scanty
    1.12
     stored
    1.09
     readily
    1.06
     fragmentary
    1.05
    Activations Density 0.115%

    No Known Activations